Skills
Navigate
skills/shinpr/claude-code-workflows/recipe-front-adjust/Gen Agent Trust Hub

recipe-front-adjust

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of user-provided requests within the modification workflow.\n
  • Ingestion points: The $ARGUMENTS variable in SKILL.md is used to capture user adjustment requests.\n
  • Boundary markers: The instructions do not define clear delimiters or safety warnings to isolate user input from the rest of the agent's instructions.\n
  • Capability inventory: The skill uses file editing tools (Edit, Write, MultiEdit), subagent invocation for verification, and repository commit functions.\n
  • Sanitization: There is no evidence of validation or sanitization applied to the user request before it influences file modifications.\n- [EXTERNAL_DOWNLOADS]: The skill performs downloads from external design sources using tools like WebFetch to facilitate visual verification against specifications.\n- [COMMAND_EXECUTION]: The skill triggers repository changes and executes verification tasks, which may include caller-provided qualityCommand strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 10:09 AM
Security Audit — agent-trust-hub — recipe-front-adjust