skill-review
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve running local shell scripts, specifically
./scripts/check-versions.shand./scripts/review-skill.sh, to automate validation of YAML syntax, package versions, and broken links. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because its primary function is to ingest and analyze untrusted external data.
- Ingestion points: The skill reads source files of other skills (SKILL.md, scripts, bundled resources) and fetches external content from the web (official API documentation, npm registry, and GitHub repositories) using the WebFetch tool.
- Boundary markers: The process description does not include specific delimiters or instructions for the agent to ignore potentially malicious embedded commands within the audited data.
- Capability inventory: The skill possesses high-privilege capabilities including Bash for shell execution, Edit and Write for local file system modification, and WebFetch for network access.
- Sanitization: There is no mention of sanitizing or validating the contents of the files being audited before they are processed by the agent.
Audit Metadata