deepinit
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data including source code, Git history, issues, and PR comments to generate instructions for AGENTS.md files. This content could be manipulated by external contributors to inject instructions into the generated guidance.
- Ingestion points: Git history, issues, PRs, and repository source code are used as evidence (Workflow section in SKILL.md).
- Boundary markers: No explicit delimiters or warnings are described to differentiate untrusted repository content from the agent's instructions.
- Capability inventory: The skill is capable of modifying or creating AGENTS.md files throughout the repository hierarchy.
- Sanitization: No sanitization, filtering, or validation of the ingested external content is described in the workflow.
Audit Metadata