answeroverflow
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from Discord discussions indexed by Answer Overflow. Since this content is user-generated and originates from external communities, it represents an indirect prompt injection surface where malicious instructions could be embedded in the retrieved data.
- Ingestion points: Thread content fetched via
web_fetchfromhttps://www.answeroverflow.com/m/<message-id>inSKILL.md. - Boundary markers: Absent; the instructions do not include specific delimiters or warnings for the agent to ignore instructions found within the fetched thread markdown.
- Capability inventory: The skill utilizes
web_searchandweb_fetchto retrieve external data from Discord conversations. - Sanitization: Absent; no mention of filtering, escaping, or sanitizing the retrieved Discord message content before it is processed by the agent.
Audit Metadata