angular-best-practices-rules-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No direct malicious code, obfuscation, or persistence mechanisms were detected within the skill's logic.
  • [COMMAND_EXECUTION]: No unauthorized system commands were found. The skill's configuration explicitly forbids package installation commands in the documentation it audits.
  • [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were identified. Network usage is dedicated to legitimate research.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the processing of rule files.
  • Ingestion points: Rule files are read from the local filesystem using the Read and Grep/Glob tools.
  • Boundary markers: The prompt templates lack delimiters or instructions to ignore embedded commands within the rule files.
  • Capability inventory: The skill utilizes WebSearch and WebFetch, which could be abused if malicious instructions are present in the rule files.
  • Sanitization: No sanitization or validation of external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 03:11 PM