skill-improve

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It reads content from .claude/skills/[name]/SKILL.md to diagnose issues and propose fixes. If the skill being processed contains malicious instructions masquerading as data, the agent might follow them during the analysis phase.
  • Ingestion points: Reads external skill files at .claude/skills/[name]/SKILL.md in Phase 3.
  • Boundary markers: Absent. The skill does not use specific delimiters or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: Includes the ability to write to the file system (Write) and execute shell commands (Bash).
  • Sanitization: No sanitization or validation of the input skill content is performed before the agent processes it for diagnosis.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to perform git operations (git checkout) and execute other platform commands (/skill-test). While these are used for the intended purpose of testing and reverting changes, they represent a capability that could be misused if the agent is compromised via indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:45 PM