skill-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a localized developer utility for file auditing and measurement. It uses standard system commands (
wc) and perform file edits only upon explicit user request. - [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content from the files it reviews (SKILL.md, reference files, and scripts), which presents an inherent surface for indirect prompt injection.
- Ingestion points: Reads content from
SKILL.md,scripts/,references/, andassets/to perform audits. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the reviewed content.
- Capability inventory: The skill has the capability to read files, write file modifications, and execute basic shell commands for file measurement (
wc). - Sanitization: There is no explicit sanitization or filtering of the content being read before it is processed by the agent.
Audit Metadata