request-validator-generator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing external user queries.
- Ingestion points: The skill triggers on highly common phrases like "request", "request generator", and "request validator generator", leading to frequent ingestion of untrusted user input into the agent's context (SKILL.md).
- Boundary markers: The instructions lack explicit delimitation or guidelines for the agent to ignore or isolate potentially malicious instructions embedded within user requests.
- Capability inventory: The skill has access to powerful system-level tools including
Bash(cmd:*),Write, andEditas listed in theallowed-toolsfrontmatter (SKILL.md). - Sanitization: There is no evidence of input validation, command sanitization, or filtering mechanisms described in the skill's logic.
Audit Metadata