seo
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the user's project files and processes them to generate reports and code modifications.
- Ingestion points: The
SKILL.mdfile instructs the agent to read all HTML files in the site source directory during the audit phase. - Boundary markers: There are no specified boundary markers or instructions to ignore embedded commands (such as those hidden in HTML comments) within the ingested files.
- Capability inventory: The agent has the capability to read project files and write modifications back to the local file system to apply the suggested SEO fixes.
- Sanitization: No sanitization, validation, or filtering logic is provided to ensure the ingested content does not contain instructions that override the agent's behavior.
Audit Metadata