anycap-human-interaction
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted feedback from humans or external web pages and uses it in subsequent prompts for image generation or video analysis.
- Ingestion points: Results from
anycap annotate poll(SKILL.md). - Boundary markers: No delimiters or ignore instructions are used when interpolating human feedback into prompts.
- Capability inventory: The agent can execute
anycap image generateandanycap actions video-read(SKILL.md). - Sanitization: The skill does not describe any validation or escaping of human-provided labels before they are used as instructions for AI models.
- [EXTERNAL_DOWNLOADS]: The skill depends on the external
anycapCLI tool and communicates with theanycap.aidomain to manage annotation sessions.
Audit Metadata