hedra-character-video

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructional content for the agent to follow, with no evidence of attempts to bypass safety filters or override system instructions.
  • [DATA_EXFILTRATION]: Communication is directed to official Hedra API endpoints. The skill appropriately advises the use of environment variables for sensitive credentials like HEDRA_API_KEY and LIVEKIT_API_KEY, preventing credential exposure.
  • [EXTERNAL_DOWNLOADS]: Dependencies mentioned, such as the Hedra creation tool and LiveKit agents, are standard libraries for integrating with the specified services and originate from appropriate sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external media and text scripts. While this represents a data ingestion surface, the skill includes explicit instructions for the agent to validate consent and content safety, providing procedural safeguards against misuse.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:51 PM
Security Audit — agent-trust-hub — hedra-character-video