work-explainer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it processes and interprets untrusted data from multiple sources to generate its educational breakdown.
  • Ingestion points: The skill explicitly reads git diff, git log, and the current conversation history (including user feedback and discussed errors) as inputs for Phase 1.
  • Boundary markers: Absent. There are no instructions to the agent to treat data from git history or conversation logs as untrusted or to ignore embedded instructions within that content.
  • Capability inventory: The skill utilizes file-writing capabilities to create new markdown files within the {CWD}/work-explainer/ directory.
  • Sanitization: Absent. There is no evidence of validation or filtering of the content retrieved from the git history or the conversation before it is used to structure the teaching output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:31 AM
Security Audit — agent-trust-hub — work-explainer