pseo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes content from the user's codebase which could contain malicious instructions.
- Ingestion points: Data enters the agent's context through the use of
Read,Glob,Grep, andBashtools during the framework detection, data architecture assessment, and SEO review steps (SKILL.md). - Boundary markers: The instructions do not define clear delimiters or "ignore previous instructions" warnings when handling content from the audited files.
- Capability inventory: The skill has access to
Bash, which provides significant command execution capabilities if the agent is manipulated via injected content (SKILL.md). - Sanitization: There is no evidence of sanitization, escaping, or schema validation for the data ingested from the project files.
Audit Metadata