reports
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism for the agent to process and analyze external content like briefings and research reports to validate embedded links. This creates a surface for indirect prompt injection where the agent ingests untrusted data from the web. Ingestion points: External content via tools like search and get_page. Boundary markers: None explicitly mentioned in the instructions. Capability inventory: File writing, network access, and repository status checks. Sanitization: No specific filtering or sanitization logic is described.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the 'git status' command within the brain repository to verify that linked files are committed and pushed.
Audit Metadata