blog-seo-check
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes untrusted data from external sources and project files.
- Ingestion points: The skill uses WebFetch to retrieve content from user-provided URLs and reads local project files in SKILL.md (Step 1).
- Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data being analyzed.
- Capability inventory: The skill utilizes
WebFetch(network operations), andGrep/Glob(file system searching) in SKILL.md (Step 5 and Step 6). - Sanitization: No validation, escaping, or filtering of external content is specified before the agent processes the data for SEO validation.
- [COMMAND_EXECUTION]: The skill instructs the agent to use file-system search tools to analyze project structure.
- Evidence: In SKILL.md (Step 5), the agent is directed to 'Use Grep and Glob to scan the project for existing blog content'. While this is aligned with the skill's purpose of checking bidirectional links, it provides a mechanism for scanning sensitive project areas if redirected by a malicious input.
Audit Metadata