Skills
Navigate
skills/venomous2/opencode-seo/retrieval-optimization/Gen Agent Trust Hub

retrieval-optimization

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts to perform search data retrieval and report publishing.
  • Evidence: python scripts/dfs_client.py and python scripts/report_publish.py are called with user-supplied and domain-specific arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites, which could contain hidden instructions targeting the LLM.
  • Ingestion points: Content is fetched from target URLs via the webfetch tool in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate the fetched external content from the agent's instructions.
  • Capability inventory: The agent can execute local scripts (scripts/dfs_client.py, scripts/report_publish.py) and write files to local directories (defined by the SEO_REPORTS_DIR environment variable).
  • Sanitization: There is no evidence of filtering or sanitizing the content retrieved from external URLs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 08:55 AM