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
Bashtool to interact with the local file system and execute subcommands of thewatch-skillutility (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 thewatch-skill batchcommand 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 viaBashand read files via theReadtool 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