audit-context-building
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface inherent to its purpose as a code analysis tool.\n
- Ingestion points: Data enters the agent context through the
<target-path>provided for analysis, which may contain untrusted code, as described in Phase 1 (Initial Reconnaissance) and Phase 2 (Deep Analysis).\n - Boundary markers: There are no specific delimiters or instructions defined in the skill to isolate the content of the analyzed files or to warn the agent against executing instructions found within them.\n
- Capability inventory: The skill utilizes powerful tools including
Read,Glob,Grep,Bash, andWriteas specified in theSKILL.mdtoolset.\n - Sanitization: The skill does not implement sanitization, escaping, or validation of the content of the analyzed source code before processing.
Audit Metadata