team-management
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script,
scripts/check-output.py, which is intended to be executed by the agent to validate management deliverables. - Evidence: The script is defined in the
scripts/directory and referenced inSKILL.mdunder execution artifacts and agent routing logic. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate management artifacts, which are subsequently read by a validation script, creating a minor attack surface.
- Ingestion points: User requests for 1:1 templates, OKR drafts, and feedback scripts in
SKILL.md. - Boundary markers: Absent; instructions do not specify delimiters or warnings to ignore embedded instructions in user data.
- Capability inventory: The
scripts/check-output.pyscript has the capability to read files from the local filesystem. - Sanitization: The validation script reads text using
errors="replace"but does not perform sanitization or security validation on the content.
Audit Metadata