team-discover
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process content from external documentation files (CDRs, PDRs, ADRs).
- Ingestion points: The skill instructions specify scanning a 'CDR index' and reading 'full module bodies' from paths like
context_modules/personas/admin.md(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested modules are provided.
- Capability inventory: The skill facilitates reading documentation files but does not involve shell execution, file writing, or network operations.
- Sanitization: No sanitization or validation of the ingested module content is mentioned.
- [SAFE]: The skill consists entirely of instructional text without any executable scripts or configuration that performs network calls, credential access, or privilege escalation. The identified ingestion surface is limited to project documentation files.
Audit Metadata