re-verify-structure
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a 'Critic' by reading and analyzing external source code and metadata artifacts (manifest.json, structure-map.md), creating an attack surface where instructions embedded in these files could influence agent behavior.
- Ingestion points: The agent is instructed to read file content in Step 1 (manifest and structure map), Step 2 (source code files), and Step 3 (searching for patterns in code).
- Boundary markers: The instructions lack explicit boundary markers or system instructions to treat the ingested file content strictly as data, which increases the risk of the LLM following instructions embedded in the comments or strings of the analyzed source code.
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andReadto perform its verification and reporting tasks. - Sanitization: There is no mention of sanitizing or escaping the content retrieved from external files before it is processed or used to generate the verification report.
Audit Metadata