feature-agents
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): This skill does not contain any executable scripts or binary files. It consists of structural documentation and system prompts for guiding AI behavior.
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface detected. 1. Ingestion points: The agents ingest arbitrary files from a codebase for analysis (as described in references/code-explorer.md and references/code-architect.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are present in the provided prompts. 3. Capability inventory: The skill itself contains no code or tools, although it is designed to be used in conjunction with a Task tool. 4. Sanitization: No sanitization or validation of the ingested codebase content is specified in the prompts.
- [DATA_EXFILTRATION] (SAFE): No network calls or sensitive file access patterns (e.g., SSH keys, credentials) were found in the skill content.
Audit Metadata