coo-advisor

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts ops_efficiency_analyzer.py and okr_tracker.py as part of its operational efficiency and OKR tracking functions.
  • [PROMPT_INJECTION]: The skill is configured to ingest and process data from company-context.md before responding. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in the context file could potentially influence the agent's behavior or script execution.
  • Ingestion points: company-context.md (referenced in SKILL.md).
  • Boundary markers: Absent; the skill instructs the agent to read the context file without defining delimiters or instructions to ignore embedded commands.
  • Capability inventory: The agent can execute local Python scripts and invoke other roles using the [INVOKE:role|question] syntax.
  • Sanitization: No input validation or sanitization is specified for the data ingested from the external context file.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:07 PM
Security Audit — agent-trust-hub — coo-advisor