deepapi
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various untrusted external sources, creating an attack surface for indirect prompt injection.\n
- Ingestion points: The skill reads content from external websites, social media profiles (LinkedIn, X/Twitter, GitHub), YouTube transcripts, and workspace emails as defined in
references/detailed-guide.md.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its operational instructions and the potentially untrusted data it retrieves from external sources.\n
- Capability inventory: The skill allows the agent to perform authenticated network requests (POST/GET) to the DeepAPI service and write generated image data to local files.\n
- Sanitization: No explicit sanitization, filtering, or validation steps are defined for the content scraped from the web or read from emails before the agent processes it.
Audit Metadata