seo
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. * Ingestion points: External HTML content fetched via WebFetch (SKILL.md). * Boundary markers: None present; the skill lacks instructions to ignore embedded instructions. * Capability inventory: The agent can modify local source files, including Nuxt and Astro configurations, in fix mode as defined in SKILL.md. * Sanitization: No validation or sanitization of external content is performed.
- [DATA_EXFILTRATION]: The skill discloses an absolute local directory path /Users/martinpammesberger/Documents/psquared/psquared-websites/ in SKILL.md, exposing a username and local file structure.
Audit Metadata