safety-training

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from a codebase.
  • Ingestion points: Data enters the agent context through the $ARGUMENTS variable and via the automated reading of project files and competency data structures defined in the phases.
  • Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded in the files being analyzed.
  • Capability inventory: The agent is authorized to read local files, write reports to the docs/ directory, and append telemetry to ~/.claude/projects/skill-telemetry.md.
  • Sanitization: There is no evidence of content sanitization or validation before the data is processed for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:58 AM
Security Audit — agent-trust-hub — safety-training