Skills
Navigate
skills/posthog/ai-plugin/context-layer-health-check/Gen Agent Trust Hub

context-layer-health-check

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is instructed to execute local scripts scripts/lint and scripts/lint --report to perform its health check tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and processes untrusted data which could potentially contain malicious instructions. 1. Ingestion points: The agent reads data from git log --merges and various wiki content pages. 2. Boundary markers: No specific delimiters or safety instructions are provided to distinguish between data and instructions during processing. 3. Capability inventory: The skill has the capability to write to the file system (editing the wiki) and execute shell commands (scripts/lint). 4. Sanitization: The instructions do not specify any validation or sanitization of the ingested git logs or wiki content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:39 AM
Security Audit — agent-trust-hub — context-layer-health-check