pov-vlog-presence
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to fetch and analyze data from numerous external URLs to determine the 'structural traits' of video prompts. This establishes an indirect prompt injection surface where instructions hidden in the external text or media metadata could potentially influence the agent's logic.
- Ingestion points: The agent is directed to read and inspect multiple external links from goodcase.ai and x.com as defined in the 'references/cases.md' file.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the external content as data-only or to ignore embedded instructions.
- Capability inventory: The agent is expected to use browser tools and multimodal inspection (image/video) to process the external assets.
- Sanitization: No sanitization or validation of the remote content is specified in the workflow.
- [EXTERNAL_DOWNLOADS]: The skill relies on a large index of external references hosted on goodcase.ai and x.com. The workflow mandates that the agent must 'inspect the anchor's finished media' on every invocation, requiring the agent to connect to and process data from these third-party domains.
Audit Metadata