deslop

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted data (code diffs) which may contain instructions masquerading as code or comments to influence the agent's cleanup behavior.
  • Ingestion points: Processes code diffs and file content comparing the current branch to 'main' (SKILL.md).
  • Boundary markers: None. The instructions do not specify using delimiters or explicit warnings to ignore instructions embedded within the code being analyzed.
  • Capability inventory: The skill's purpose involves reading and modifying source code files.
  • Sanitization: No sanitization or validation of the input code is mentioned to prevent instruction leakage from the code into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 08:52 AM
Security Audit — agent-trust-hub — deslop