to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted inputs from the conversation history and project codebase to generate documentation.
- Ingestion points: The agent is instructed to explore the repository and synthesize the conversation history (found in SKILL.md).
- Boundary markers: The prompt lacks explicit delimiters or instructions to ignore embedded commands within the ingested codebase or conversation context.
- Capability inventory: The skill has read access to the repository and write access to an external issue tracker.
- Sanitization: No validation or sanitization of the synthesized content is performed before it is published to the issue tracker.
Audit Metadata