skills/terrylica/cc-skills/health/Gen Agent Trust Hub

health

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform diagnostic checks on the host system, including process verification using PID files in /tmp, checking launchd job status, and querying the 1Password CLI (op).
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and outputs the contents of audit logs and temporary JSON circuit breaker files. This ingestion of untrusted or externally-modifiable data into the agent's context represents a potential prompt injection surface. 1. Ingestion points: Reads files from /tmp/calcom-sync-circuit.json, /tmp/calcom-commander-agent-circuit.json, and the latest .ndjson file in the audit log directory. 2. Boundary markers: Content from these files is printed directly to the output without delimiters or ignore-instructions wrappers. 3. Capability inventory: The skill has access to the Bash tool, allowing for broad system interaction. 4. Sanitization: There is no sanitization or validation of the content read from the audit logs or JSON files before it is presented to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 02:12 AM