ts-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user-provided content via the $ARGUMENTS variable.
- Ingestion points: User-supplied code or pull request diffs are interpolated into SKILL.md through the $ARGUMENTS placeholder.
- Boundary markers: Absent. The skill lacks delimiters (like XML tags or triple backticks with explicit instructions) to separate the untrusted code from the review instructions.
- Capability inventory: While the skill instructions are benign, the agent executing it typically has access to file system operations and shell commands which could be targeted by an injection attack hidden in the code being reviewed.
- Sanitization: No sanitization or validation of the input is performed before processing.
Audit Metadata