function-length-and-responsibility

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file defines a mandatory Memory Protocol that instructs the agent to execute 'cat .claude/context/memory/learnings.md' before starting a task. This is a standard pattern for context management in certain agent environments.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to review and process arbitrary project files (using the glob '**/.').
  • Ingestion points: Project files matching the global pattern are ingested via the Read and Edit tools.
  • Boundary markers: Absent; the instructions do not define delimiters for user-provided code or provide instructions to ignore embedded commands within the files.
  • Capability inventory: The skill utilizes Read, Write, and Edit tools, and allows for shell command execution through its memory protocol.
  • Sanitization: Absent; there is no evidence of content filtering or sanitization of the files being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 08:15 AM
Security Audit — agent-trust-hub — function-length-and-responsibility