code-antipatterns-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes external codebase files, creating an indirect prompt injection surface where malicious instructions embedded in comments or code could attempt to influence the agent's analysis or subsequent actions.\n
  • Ingestion points: Processes project files via ast-grep, Grep, Read, and Glob tools as described in the analysis strategy (SKILL.md).\n
  • Boundary markers: The instructions do not specify any delimiters or explicit directives to the agent to ignore natural language instructions found within the scanned source files.\n
  • Capability inventory: Employs Bash, ast-grep, Grep, and jq to read, search, and parse file data, which are then summarized for the user (SKILL.md).\n
  • Sanitization: There is no evidence of sanitization or filtering of the scanned content to prevent embedded instructions from affecting the agent's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 02:29 PM