chief-of-staff
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill establishes a workflow for an AI agent to act as a 'Chief of Staff', focusing on strategic coordination and tribal knowledge preservation. It utilizes a markdown-based wiki for persistent storage and references other local skills by relative path for specific tasks. No unauthorized network operations, credential access, or malicious commands were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection as its core functionality involves reading and processing data from external sources, including subagent reports, research notes, and potentially user-controlled project metadata.
- Ingestion points: Markdown wiki pages, subagent reports, research notes, pull request transcripts, and issue tracker content mentioned in
SKILL.md. - Boundary markers: Not specified; instructions do not mandate the use of delimiters or 'ignore' instructions for external data.
- Capability inventory: Orchestration and delegation of tasks to subagents, and following instructions from other local skills like
../retro/SKILL.md. - Sanitization: No validation or sanitization of ingested content is described in the instructions.
Audit Metadata