blog-seo-check
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from external URLs and local files that could contain malicious instructions.\n
- Ingestion points: Content is ingested from local files and URLs in Step 1, and external links are processed in Step 6 via WebFetch.\n
- Boundary markers: There are no specified delimiters or instructions to treat ingested content as untrusted data, increasing the risk that embedded instructions might be followed by the agent.\n
- Capability inventory: The agent uses WebFetch for network access and Grep/Glob for local file system access.\n
- Sanitization: No sanitization or filtering of the ingested content is performed before it is analyzed by the agent.\n- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration without any standalone scripts or binary files, which minimizes the risk of direct malicious code execution or persistence.
Audit Metadata