chief-of-staff

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were identified. All references to external skills are within the same vendor ecosystem (borghei).
  • [NO_CODE]: The skill consists entirely of natural language instructions and metadata in Markdown format. It does not include or execute any scripts or binary files.
  • [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection due to its processing of untrusted data.
  • Ingestion points: Founder questions (user-provided) and company context/decision history files are loaded into the agent's context in SKILL.md.
  • Boundary markers: Absent. The skill does not define clear delimiters or instructions to ignore potential commands within the data being processed.
  • Capability inventory: The skill orchestrates multiple downstream sub-skills (CEO, CTO, Board Meeting, etc.) and uses a decision-logger. It could potentially pass malicious instructions from the input to these tools.
  • Sanitization: There is no specified logic for validating or escaping user-provided questions before they are used in routing or synthesis protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:13 AM