skills/affaan-m/ecc/videodb/Gen Agent Trust Hub

videodb

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the videodb Python SDK and python-dotenv package from the official Python Package Index (PyPI) to facilitate interaction with the VideoDB service.
  • [COMMAND_EXECUTION]: Executes the bundled scripts/ws_listener.py script and utilizes inline Python commands via the Bash tool to manage session metadata and process real-time events.
  • [DATA_EXFILTRATION]: Ingests and transmits media data from local files, public URLs, and live RTSP/RTMP streams to the VideoDB cloud infrastructure for processing and indexing as part of its core functionality.
  • [PROMPT_INJECTION]: Potential indirect prompt injection surface detected:
  • Ingestion points: Ingests external content from third-party URLs (coll.upload(url=...)) and live streams (coll.connect_rtstream(...)) as documented in SKILL.md and reference/rtstream-reference.md.
  • Boundary markers: Untrusted transcript data and visual descriptions are interpolated into prompts for the coll.generate_text method without explicit delimiters in the provided usage examples.
  • Capability inventory: The agent has access to Bash and python tools, allowing it to execute the VideoDB SDK for file system operations and network requests.
  • Sanitization: No explicit sanitization or filtering of transcribed text or visual AI descriptions is performed before the content is passed back into the LLM context for summarization or analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:48 PM
Security Audit — agent-trust-hub — videodb