triage-better-typescript
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's workflow for analyzing user feedback and code remediations introduces a surface for indirect prompt injection.
- Ingestion points: Untrusted user feedback, TypeScript source code, and git diffs are ingested into the agent context as specified in
SKILL.md. - Boundary markers: The instructions do not define boundary markers or explicit instructions to disregard embedded commands within the processed data in
SKILL.md. - Capability inventory: The skill requires the ability to execute tests and type-check code, representing a capability tier that could be targeted via malicious input (as noted in
SKILL.md). - Sanitization: No sanitization, validation, or filtering of the ingested source code or feedback is specified in
SKILL.md.
Audit Metadata