Skills
skills/eligapris/codebase-5yr-forecast-skill/codebase-5yr-forecast/Gen Agent Trust Hub

codebase-5yr-forecast

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/codebase_scanner.py executes git log and git remote via subprocess.run to extract repository metadata.
  • [EXTERNAL_DOWNLOADS]: The skill clones remote GitHub repositories into a temporary directory to perform its analysis phase.
  • [PROMPT_INJECTION]: The skill processes untrusted codebase files and web search results, making it susceptible to indirect prompt injection. Ingestion points: reads source code and manifest files; fetches web data. Boundary markers: no explicit markers or safety instructions are defined for ingested content. Capability inventory: the skill can execute shell commands and file system operations. Sanitization: no evidence of content sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:33 PM
Security Audit — agent-trust-hub — codebase-5yr-forecast