product-help
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to provide product support by retrieving information from the official vendor domain (chatcut.io). No malicious behaviors or unauthorized system access were detected.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes content from the external web. However, the risk is mitigated by the source being the official vendor documentation.
- Ingestion points: Web retrieval via search and page-reading from https://chatcut.io/docs, releases, and changelog.
- Boundary markers: Explicit instructions to only cite opened official pages and avoid answering from memory or snippets.
- Capability inventory: Limited to web retrieval and decision routing; no file-writing or command execution capabilities are present.
- Sanitization: Output is restricted to verified terms and names found in official docs.- [PROMPT_INJECTION]: The skill contains instructions to not expose internal implementation details, release automation, or review notes. While flagged as concealment by static analysis, this is a benign business requirement for confidentiality and does not represent an attempt to hide malicious agent behavior.
Audit Metadata