sherlock-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill is designed to process untrusted data such as pull request descriptions, commit messages, and code diffs.
- Ingestion points: Processes external data via
git diff,git log, and PR descriptions inSKILL.md. - Boundary markers: Uses structured markdown templates for investigations but does not include explicit instructions to ignore embedded prompts in reviewed data.
- Capability inventory: References the use of shell commands like
gitandnpm testfor evidence gathering. - Sanitization: No explicit sanitization of reviewed content is defined, which is standard for an investigative tool where the user/agent is expected to interpret the data critically.
- Command Execution (SAFE): The skill suggests the use of standard development commands (
git,npm test). These are consistent with the skill's primary purpose of code review and are not used for malicious privilege escalation or persistence.
Audit Metadata