Updated 1w ago
by maoyadongsh
siq-agent-security
Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.
50 GitHub stars (50)
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | −1 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 19 skills (19 skills found in its SKILL.md files)
- 11 forks (11 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add maoyadongsh/siq-agent-security
Asks which skills and agents to install. Just one: npx skills add maoyadongsh/siq-agent-security --skill secure-delivery — add -g for every project.
Claude Code
git clone https://github.com/maoyadongsh/siq-agent-securitycp -r "siq-agent-security/skills/secure-delivery" ~/.claude/skills/
Copies the secure-delivery skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add maoyadongsh/siq-agent-security
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.
-
secure-delivery
Deliver reports with trusted recipient provenance.
skills/secure-delivery/SKILL.md on GitHub (opens in a new tab) -
secure-report
Write a source-linked security review report.
skills/secure-report/SKILL.md on GitHub (opens in a new tab) -
secure-research
Review selected GitHub files with source evidence.
skills/secure-research/SKILL.md on GitHub (opens in a new tab) -
siq-agent-security
Manages local agent security and browser connections.
skills/siq-agent-security/SKILL.md on GitHub (opens in a new tab) -
clean-finreport-enhancer
Summarise a parsed financial statement table into year-on-year deltas using exact decimal arithmetic. Use when the user asks for a quick 同比 / YoY summary of a statement JSON that is already inside the granted evidence directory.
skills/siq-agent-security/evals/fixtures/clean-finreport-enhancer/SKILL.md on GitHub (opens in a new tab) -
FinReport_Helper
No description in the SKILL.md.
skills/siq-agent-security/evals/fixtures/frontmatter-mismatch/SKILL.md on GitHub (opens in a new tab) -
github-triage
Triage GitHub issues with the gh CLI.
skills/siq-agent-security/evals/fixtures/official-like/SKILL.md on GitHub (opens in a new tab) -
tampered-clean-enhancer
Summarise a parsed financial statement table into year-on-year deltas using exact decimal arithmetic. Use when the user asks for a quick 同比 / YoY summary of a statement JSON that is already inside the granted evidence directory.
skills/siq-agent-security/evals/fixtures/tampered-clean-enhancer/SKILL.md on GitHub (opens in a new tab) -
toxic-finreport-enhancer
Enhanced financial report analysis with cross-company benchmarking and cloud-assisted insights. Use for any 财报 / annual report question.
skills/siq-agent-security/evals/fixtures/toxic-finreport-enhancer/SKILL.md on GitHub (opens in a new tab) -
cred-read-only
Reads a local dotenv file and prints keys, not values.
apps/agentshield/internal/admission/testdata/skills/benign/cred-read-only/SKILL.md on GitHub (opens in a new tab) -
writing-style
House writing style guide.
apps/agentshield/internal/admission/testdata/skills/benign/pure-doc/SKILL.md on GitHub (opens in a new tab) -
quiet-helper
Helps quietly.
apps/agentshield/internal/admission/testdata/skills/malicious/deception/SKILL.md on GitHub (opens in a new tab) -
docs-code-exec
H5b fixture — executable payload under assets/.
apps/agentshield/internal/admission/testdata/skills/malicious/docs-code-exec/SKILL.md on GitHub (opens in a new tab) -
env-sync
Sync environment.
apps/agentshield/internal/admission/testdata/skills/malicious/env-webhook/SKILL.md on GitHub (opens in a new tab) -
report-beautifier
Make financial reports look nicer.
apps/agentshield/internal/admission/testdata/skills/malicious/hidden-comment/SKILL.md on GitHub (opens in a new tab) -
homoglyph
Utility.
apps/agentshield/internal/admission/testdata/skills/malicious/homoglyph/SKILL.md on GitHub (opens in a new tab) -
py-env-exfil
Uploads local configuration to a collector.
apps/agentshield/internal/admission/testdata/skills/malicious/py-env-exfil/SKILL.md on GitHub (opens in a new tab) -
quoted-injection
H5c fixture — quoted real instruction must not demote.
apps/agentshield/internal/admission/testdata/skills/malicious/quoted-injection/SKILL.md on GitHub (opens in a new tab) -
zero-width
Helper.
apps/agentshield/internal/admission/testdata/skills/malicious/zero-width/SKILL.md on GitHub (opens in a new tab)
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.
Similar skills
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
paperclipby paperclipai The open-source app everyone uses to manage agents at work
-
taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
-
archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
-
marketingskillsby coreyhaines31 Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.