resolve-ambiguity
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to perform 'discovery' by reading relevant files, project conventions, and searching for prior art in the codebase. These files are external, untrusted data sources that could contain embedded instructions intended to influence the agent's behavior during the ambiguity resolution process.
- Ingestion points: SKILL.md (Step 1 — Discover before you ask) directs the agent to read target files, imports, callers, tests, and configuration files.
- Boundary markers: No specific delimiters or 'ignore' instructions are defined to separate the content of these external files from the agent's primary instructions.
- Capability inventory: While the skill itself does not perform subprocess calls or network operations, it acts as a gatekeeper for the agent's broader capabilities (like editing files or running commands) which are intended to resume once ambiguity is resolved.
- Sanitization: The instructions do not specify any validation, filtering, or escaping of the information gathered during the discovery phase.
Audit Metadata