add-reporter

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of untrusted user input.\n
  • Ingestion points: The $ARGUMENTS variable is used to dynamically generate file paths (e.g., megalinter/reporters/<Name>Reporter.py) and branch names (e.g., user/add-<reporter-name>-reporter).\n
  • Boundary markers: Absent. There are no instructions or delimiters defining how the agent should interpret or validate the $ARGUMENTS content to ensure it does not deviate from the intended name format.\n
  • Capability inventory: The skill enables the use of Read, Grep, Glob, Edit, and Write tools (defined in SKILL.md frontmatter), which collectively allow for arbitrary file system access and modification.\n
  • Sanitization: Absent. The instructions lack validation or sanitization logic, which could allow a malicious user to provide a reporter name containing path traversal sequences or unexpected characters to influence the agent's file system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:55 PM
Security Audit — agent-trust-hub — add-reporter