video-memory

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to interact with the local file system and execute subcommands of the watch-skill utility (list, search, ask, batch) to manage and query the video index.- [INDIRECT_PROMPT_INJECTION]: The skill indexes and processes content from videos (OCR text and transcripts) which constitutes untrusted data.- Ingestion points: Data is collected from video files via the watch-skill batch command and stored in ~/.watch-skill/ for later retrieval.- Boundary markers: The instructions do not provide explicit delimiters or guidance for the agent to distinguish between its instructions and content indexed from the videos.- Capability inventory: The agent has the ability to execute shell commands via Bash and read files via the Read tool based on the data retrieved from the index.- Sanitization: No specific sanitization or filtering mechanisms are described to validate the indexed content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 12:04 AM
Security Audit — agent-trust-hub — video-memory