faq-seo
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided keywords, product details, and competitor information to generate SEO strategy documents, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: User-defined fields within
templates/output-template.md(e.g., Company, ICP, Target keywords). - Boundary markers: Absent; the instructions do not provide delimiters or warnings to isolate untrusted data.
- Capability inventory: Includes local script execution (
scripts/check-output.py) and file writing capabilities. - Sanitization: Absent; no input validation or filtering is defined for the processed data.
- [COMMAND_EXECUTION]: The skill includes a local validation utility,
scripts/check-output.py, designed to verify that the generated SEO deliverables contain required terms. The script operates locally on provided paths and does not exhibit malicious behavior such as network access or privilege escalation.
Audit Metadata