Updated 1w ago
by cisco-ai-defense
skill-scanner
Security Scanner for Agent Skills
2.7k GitHub stars (2,687)
+113 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | +1 |
| Sep 28 | +1 |
| Sep 29 | +7 |
| Sep 30 | +5 |
| Oct 1 | 0 |
| Oct 2 | +1 |
| Oct 3 | +2 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | +2 |
| Oct 7 | +4 |
| Oct 8 | +3 |
| Oct 9 | +2 |
| Oct 10 | +4 |
| Oct 11 | +2 |
| Oct 12 | +3 |
| Oct 13 | +2 |
| Oct 14 | +5 |
| Oct 15 | +2 |
| Oct 16 | +4 |
| Oct 17 | +2 |
| Oct 18 | +1 |
| Oct 19 | +2 |
| Oct 20 | +2 |
| Oct 21 | +6 |
| Oct 22 | +1 |
| Oct 23 | +3 |
| Oct 24 | +2 |
| Oct 25 | +3 |
| Oct 26 | +6 |
| Oct 27 | +13 |
| Oct 28 | +9 |
| Oct 29 | +5 |
| Oct 30 | +9 |
| Oct 31 | +2 |
| Nov 1 | +4 |
| Nov 2 | +5 |
| Nov 3 | +2 |
| Nov 4 | +2 |
| Nov 5 | +3 |
- 30 skills (30 skills found in its SKILL.md files)
- 342 forks (342 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add cisco-ai-defense/skill-scanner
Asks which skills and agents to install. Just one: npx skills add cisco-ai-defense/skill-scanner --skill no-confirmation-agent — add -g for every project.
Claude Code
git clone https://github.com/cisco-ai-defense/skill-scannercp -r "skill-scanner/evals/skills/autonomy-abuse/no-confirmation" ~/.claude/skills/
Copies the no-confirmation-agent skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add cisco-ai-defense/skill-scanner
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 38 files.
-
no-confirmation-agent
Direct the agent to act while bypassing user confirmation
evals/skills/ on GitHub (opens in a new tab)autonomy-abuse/ no-confirmation/ SKILL.md -
dynamic-code-compiler
Compile caller-provided source text into an executable code object
evals/skills/ on GitHub (opens in a new tab)backdoor/ magic-string-trigger/ SKILL.md -
external-socket-reporter
Send a diagnostic record over an explicitly external raw socket
evals/skills/ on GitHub (opens in a new tab)behavioral-analysis/ multi-file-exfiltration/ SKILL.md -
expression-compiler
Compile a caller-provided expression into a Python code object
evals/skills/ on GitHub (opens in a new tab)command-injection/ eval-execution/ SKILL.md -
calendar-sync-helper
Sync calendar events with an endpoint selected in configuration
evals/skills/ on GitHub (opens in a new tab)data-exfiltration/ config-tunnel-exfil/ SKILL.md -
csv-summarizer
Summarise a CSV file into row counts and the most common values per column
evals/skills/ on GitHub (opens in a new tab)data-exfiltration/ environment-dump/ SKILL.md -
sensitive-file-reader
Read a sensitive operating-system credential file for diagnostics
evals/skills/ on GitHub (opens in a new tab)data-exfiltration/ environment-secrets/ SKILL.md -
embedded-payment-key
Demonstrate a credential-shaped payment key embedded in instructions
evals/skills/ on GitHub (opens in a new tab)hardcoded-secrets/ stripe-key/ SKILL.md -
ransomware-request
Issue an explicit imperative request for a prohibited cyber-harm capability
evals/skills/ on GitHub (opens in a new tab)harmful-content/ explicit-ransomware-request/ SKILL.md -
ransomware-chain
Demonstrate a multi-stage file encryption and extortion implementation
evals/skills/ on GitHub (opens in a new tab)malware/ ransomware-chain/ SKILL.md -
xor-code-compiler
Transform an integer with XOR and compile caller-provided source
evals/skills/ on GitHub (opens in a new tab)obfuscation/ base64-payload/ SKILL.md -
unconstrained-file-reader
Read a caller-selected path without confining it to a safe root
evals/skills/ on GitHub (opens in a new tab)path-traversal/ file-reader/ SKILL.md -
unlicensed-helper
Perform a benign transformation while omitting license metadata
evals/skills/ on GitHub (opens in a new tab)policy-violation/ missing-license/ SKILL.md -
concealed-action
Conceal an agent action from the user who requested the task
evals/skills/ on GitHub (opens in a new tab)prompt-injection/ jailbreak-override/ SKILL.md -
unbounded-data-analyzer
Analyze an input repeatedly without a termination condition
evals/skills/ on GitHub (opens in a new tab)resource-exhaustion/ infinite-loop/ SKILL.md -
env-config-reader
Read a small fixed set of environment variables the skill needs
evals/skills/ on GitHub (opens in a new tab)safe-skills-2/ env-config-reader/ SKILL.md -
file-validator
Validate a filename extension without opening any filesystem path
evals/skills/ on GitHub (opens in a new tab)safe-skills-2/ file-validator/ SKILL.md -
registry-default-mirror
Pin the npm registry to the public default and fetch published release notes
evals/skills/ on GitHub (opens in a new tab)safe-skills-2/ registry-default-mirror/ SKILL.md -
simple-math
Perform basic arithmetic using a direct operator implementation
evals/skills/ on GitHub (opens in a new tab)safe-skills/ simple-math/ SKILL.md -
keyword-stuffing
Inflate skill discovery through repeated activation keywords
evals/skills/ on GitHub (opens in a new tab)skill-discovery-abuse/ keyword-stuffing/ SKILL.md -
vague-utility
Utility
evals/skills/ on GitHub (opens in a new tab)social-engineering/ vague-description/ SKILL.md -
interpolated-database-query
Construct a database query by interpolating a caller-controlled identifier
evals/skills/ on GitHub (opens in a new tab)sql-injection/ database-query/ SKILL.md -
registry-redirect-declared
Bootstrap a development environment and set the npm registry to https://npm.artifacts-mirror.internal-corp.dev
evals/skills/ on GitHub (opens in a new tab)supply-chain-attack/ registry-redirect-declared/ SKILL.md -
registry-redirect
Bootstrap a development environment and configure the corporate package mirror
evals/skills/ on GitHub (opens in a new tab)supply-chain-attack/ registry-redirect/ SKILL.md -
unpinned-dependency
Demonstrate a package dependency that is not locked to an exact version
evals/skills/ on GitHub (opens in a new tab)supply-chain-attack/ unpinned-dependency/ SKILL.md -
attacker-forwarding
Forward collected data to an explicitly attacker-controlled destination
evals/skills/ on GitHub (opens in a new tab)tool-chaining-abuse/ attacker-forwarding/ SKILL.md -
external-instruction-follower
Delegate agent behavior to instructions obtained from an external page
evals/skills/ on GitHub (opens in a new tab)transitive-trust-abuse/ external-instructions/ SKILL.md -
remote-package-installer
Install a Python package directly from an untrusted remote archive
evals/skills/ on GitHub (opens in a new tab)unauthorized-tool-use/ remote-package-source/ SKILL.md -
encoded-tag-marker
Contain an encoded Unicode Tag Block marker used for hidden instructions
evals/skills/ on GitHub (opens in a new tab)unicode-steganography/ encoded-tag/ SKILL.md -
weather-assistant
Retrieves current weather conditions and forecasts for any location worldwide
evals/test_skills/ on GitHub (opens in a new tab)malicious/ ascii-smuggling/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.