skill-algorithm-updates
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and fetches content from external websites which introduces a surface for indirect prompt injection if the fetched pages contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Content retrieved from external URLs using the
web_fetchtool as described inSKILL.md(Step 4). - Boundary markers: Absent. The skill does not specify the use of delimiters or instructions to ignore potential commands embedded in the external content.
- Capability inventory: Includes
web_search,web_fetch, and file-writing capabilities to theoutputs/directory. - Sanitization: The instructions do not include any steps for sanitizing, escaping, or validating the text extracted from external sources before processing.
Audit Metadata