how
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes findings gathered from the codebase and interpolates them into a synthesis prompt for a subagent. This creates an attack surface where malicious comments or data within the analyzed codebase could influence the agent's behavior.\n
- Ingestion points: The
{EXPLORER_FINDINGS_ALL}placeholder inreferences/explainer-prompt.mdreceives untrusted data gathered by explorer subagents.\n - Boundary markers: There are no delimiters or 'ignore' instructions surrounding the interpolated findings to distinguish them from the agent's primary instructions.\n
- Capability inventory: The subagents are granted read-only access to the filesystem via the
Read,Grep, andGlobtools.\n - Sanitization: No sanitization, escaping, or validation is performed on the codebase content before it is passed to the explainer subagent for synthesis.
Audit Metadata