scrub-metadata

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands including exiftool, find, mkdir, and cp to perform metadata scrubbing and file management. These operations are consistent with the skill's stated purpose and do not involve unauthorized network access.
  • [INDIRECT_PROMPT_INJECTION]: The skill is theoretically susceptible to indirect prompt injection if image metadata (processed by exiftool) contains malicious instructions intended for the agent.
  • Ingestion points: Output from exiftool is read into the agent's context during preview and verification steps (SKILL.md, Steps 3 and 6).
  • Boundary markers: None are explicitly defined for the tool output.
  • Capability inventory: The skill has access to shell execution (Bash), file reading, and file writing.
  • Sanitization: No specific filtering or sanitization of the exiftool output is performed before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 07:54 PM
Security Audit — agent-trust-hub — scrub-metadata