Skills
Navigate
skills/alirezarezvani/claude-skills/run-without-you/Gen Agent Trust Hub

run-without-you

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project configuration files and uses it to build deployment payloads and roadmaps. Malicious content in these files could potentially influence agent actions or instructions.\n
  • Ingestion points: scripts/deployment_builder.py and scripts/next_directions_writer.py read configuration from ./my-agent/build-sheet.json.\n
  • Boundary markers: No explicit markers or delimiters are used when interpolating configuration values into generated payloads or documentation.\n
  • Capability inventory: Local file writing (write_text in scripts/deployment_builder.py and scripts/next_directions_writer.py) and shell command generation for user review (curl commands printed by scripts/deployment_builder.py).\n
  • Sanitization: No input validation or sanitization is performed on the data read from configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 05:52 AM