keyword-research

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it instructs the agent to analyze and process data from external competitor URLs and third-party SEO tools.\n
  • Ingestion points: Competitor URL analysis and keyword metric retrieval from external sources as described in the workflow in SKILL.md.\n
  • Boundary markers: Absent. No specific instructions are provided to the agent to separate fetched content from internal instructions or to ignore embedded prompts.\n
  • Capability inventory: None. The skill contains no scripts or executable code; it relies on the agent's external tools (like WebFetch).\n
  • Sanitization: Absent. No filtering or validation of external content is specified before it is processed for insights.\n- [NO_CODE]: This skill consists exclusively of markdown documentation and instructional prompts; it does not include any executable scripts, binaries, or code files.\n- [SAFE]: No malicious patterns, such as hardcoded secrets, persistence mechanisms, or obfuscated content, were detected in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:29 PM