Skip to content

seb1n/awesome-ai-agent-skills / agent-security/skill-supply-chain-audit

skill-supply-chain-audit

Verified

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

FileKindSize
SKILL.mdskill md9.6 KB
agents/openai.yamlconfig223 B
assets/audit-report-template.mdmarkdown1.7 KB
references/review-checklist.mdmarkdown3.6 KB
scripts/audit_skill.pyexecutablescript34.8 KB

assets/audit-report-template.md

View on GitHub
# Agent Skill Supply-Chain Audit

## Decision

- Disposition: approve | approve-with-constraints | quarantine | reject
- Target/version:
- Target SHA-256 and canonical package-manifest hash:
- Archive canonical member-manifest hash(es), format, and inspection completeness:
- Source and publisher claim:
- Audit date:
- Method and limitations:

## Executive summary

State the observed behavior, highest material risk, required constraints, and residual uncertainty. Label each statement `observed`, `inferred`, or `unknown`.

## Coverage and skipped-content review

- Content pattern scan complete: yes | no
- Archive metadata inspection complete: yes | no | not applicable

| Path | Bytes / SHA-256 | Why skipped | Required bounded review | Owner | Resolution/status |
|---|---|---|---|---|---|
| | | | | | |

## Behavior and permission inventory

| Capability | Claim status | Evidence | Data source | Destination/write target | Required? | Constraint |
|---|---|---|---|---|---|---|
| | observed/inferred/unknown | | | | | |

## Findings

### FINDING-001 — Title

- Severity / confidence:
- Claim status: observed | inferred | unknown
- Remediation status:
- Evidence:
- Preconditions:
- Impact:
- Remediation:
- Verification:
- Residual risk:

## Provenance and change review

Record the exact source, release/commit, signatures or checksum evidence, licenses, dependency changes, and unexplained artifacts.

## Required controls

- Filesystem:
- Commands:
- Network domains:
- Accounts and scopes:
- Human approvals:
- Logging and retention:

## Verification record

List static checks, manual inspections, any authorized sandbox tests, results, and behavior not tested.

## Unanswered questions

List facts that could change the disposition and assign an owner for each.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall