video-production
Warn
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains a 'Companion check' instruction that directs the AI agent to autonomously execute shell commands (ls) against the user's filesystem when the skill is first activated. This reconnaissance targets application-specific configuration directories, including hidden paths in the user's home folder such as ~/.claude/skills/ and ~/.agent/skills/, to identify installed software and environment details without explicit user consent. The use of error suppression (2>/dev/null) indicates an intent for these operations to run silently.
Audit Metadata