chatgpt-scraper-api
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from an external API (
api.scavio.dev) that includes LLM-generated text and scraped web data. This untrusted content is introduced into the agent's context, which could potentially contain malicious instructions designed to influence the agent's subsequent actions. - Ingestion points:
SKILL.md(via processing of API response fields likeanswer.markdownandsources). - Boundary markers: Absent. The skill does not provide specific instructions or delimiters to the agent to isolate external data from its own operational logic.
- Capability inventory: The skill performs network operations via the
requestslibrary to communicate with the service provider. - Sanitization: Absent. There is no mention of sanitizing, filtering, or validating the markdown content or metadata retrieved from the external source before it is utilized by the agent.
Audit Metadata