external-gitcode-ascend-ascendc-operator-code-review

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data into its reasoning process without isolation.
  • Ingestion points: The skill accepts untrusted content through 'Parameter 1: Code Snippet', 'Parameter 2: Review Rule Description', and an optional 'Parameter 3: Specification File Path' in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the provided code snippets or descriptions.
  • Capability inventory: The skill is granted significant capabilities, including reading local files and using LSP/Grep tools to analyze code logic and dependencies.
  • Sanitization: No sanitization or validation is performed on the input parameters before they are used to drive the agent's analysis or file access operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 03:04 AM
Security Audit — agent-trust-hub — external-gitcode-ascend-ascendc-operator-code-review