reverse-engineer

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to verify configuration files and retrieve Git metadata (commit hash and date). It creates directories dynamically based on the configuration found in .stackshift-state.json.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase data to produce documentation, which is a potential vector for indirect prompt injection. Ingestion points: Codebase files accessed via Read and Glob. Boundary markers: Absent. Capability inventory: Write, Bash, and Task tools. Sanitization: No specific sanitization of the input codebase is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 09:23 AM