cognitive-load-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external codebases. Ingestion points: The agent uses Read, Grep, and Glob to ingest file contents (SKILL.md). Boundary markers: No delimiters or instructions are used to separate codebase content from agent instructions. Capability inventory: The agent has access to Bash, Write, and AskUserQuestion tools. Sanitization: The skill does not perform sanitization on ingested content before processing.
  • [COMMAND_EXECUTION]: The skill executes local shell commands to probe for the existence of analysis tools such as lizard, radon, and gocyclo, and runs its calculation logic through a local Python script using the uv run tool (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:45 AM
Security Audit — agent-trust-hub — cognitive-load-analyzer