learn-eval-deep

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script located at ~/Documents/skills-ecosystem-eval/src/learn_eval_bridge.py. It also uses shell commands like ls and head to locate and list files in the ~/.claude/skills/learned/ directory.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and processes the content of other skill files (untrusted data) to perform quality audits.
  • Ingestion points: Skill files read from ~/.claude/skills/learned/*.md.
  • Boundary markers: None. The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested content.
  • Capability inventory: The skill can execute shell commands (python3, ls) and read/write files.
  • Sanitization: No sanitization or validation of the ingested skill content is described before it is analyzed or used to suggest modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 02:14 AM