skill-curator

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a shell command in the workflow section used to index metadata from other files. The command for d in <root>/*/*/; do grep -E '^(name|description):' "$d/SKILL.md"; done is a local filesystem operation intended for inventory.
  • [PROMPT_INJECTION]: The skill's primary function involves reading and auditing external skill files, which presents a surface for indirect prompt injection where instructions embedded in those files could influence agent behavior.
  • Ingestion points: The skill reads SKILL.md files from multiple subdirectories via grep and direct file access.
  • Boundary markers: No explicit delimiters or warnings are used to separate external data from the agent's core instructions.
  • Capability inventory: The agent has access to shell commands (grep) and general file system operations for refactoring.
  • Sanitization: The instructions do not specify any validation or sanitization of the content found in the audited files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 04:23 AM
Security Audit — agent-trust-hub — skill-curator