recoup-internal-consulting-research-miner
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external "research wiki" to generate atomic content signals in the local workspace.
- Ingestion points: Content is read from an external path resolved through
integrations/research/AGENTS.md, includinglog.md,for-builders.md, and various research pages underpatterns/,artifacts/, andconcepts/. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" markers for the content retrieved from the external wiki.
- Capability inventory: The skill performs file system reads from the resolved wiki path and file system writes to the
signals/and_work/directories. - Sanitization: There is no evidence of sanitization or filtering of the markdown content retrieved from the wiki before it is processed into content angles and written to new files.
Audit Metadata