chief-of-staff
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists of markdown instructions and configuration metadata. It does not include any executable scripts, binaries, or tool definitions inside the package files (SKILL.md, agents/openai.yaml, etc.).\n- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to process external data via 'context pointers' (research notes, commits), which creates an attack surface for indirect prompt injection.\n
- Ingestion points: External research notes and commit history referenced in SKILL.md.\n
- Boundary markers: Not defined within the skill instructions.\n
- Capability inventory: No tools, subprocess calls, or executable scripts are included in this skill package.\n
- Sanitization: No validation or sanitization logic is present.\n- [SAFE]: Analysis of the instructions and metadata found no evidence of prompt injection, data exfiltration, or other malicious behaviors. References to external GitHub repositories are for provenance and source tracking and point to well-known developers.
Audit Metadata