code-review

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from external sources.
  • Ingestion points: The skill accepts 'Changed code scope' and 'Author intent' as inputs (specified in SKILL.md).
  • Boundary markers: The instructions do not define delimiters or isolation rules to distinguish the skill's directives from potentially malicious instructions embedded in the code or metadata being reviewed.
  • Capability inventory: While the skill itself does not define dangerous tools, the agent environment typically provides file system and command execution capabilities that could be targeted via injection.
  • Sanitization: There are no mechanisms described for validating or escaping external content before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 04:50 AM
Security Audit — agent-trust-hub — code-review