trinity-processor
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to query external AI platforms (ChatGPT, Gemini, Claude) and process the resulting content. This creates a vulnerability to indirect prompt injection if the data retrieved contains malicious instructions that influence the agent's behavior during summarization.
- Ingestion points: External responses from chatgpt.com, gemini.google.com, and claude.ai are processed as untrusted input (SKILL.md).
- Boundary markers: The instructions do not specify any boundary markers or delimiters to separate the retrieved data from the agent's own task instructions.
- Capability inventory: The skill implies the use of web browsing and text extraction capabilities to retrieve results from the specified AI platforms (SKILL.md).
- Sanitization: There are no instructions for sanitizing or filtering the content retrieved from the external services before processing or summarization.
Audit Metadata