radar-navigation

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute the 'radar' CLI tool with subcommands like 'query', 'refresh', and 'route add' to perform repository mapping and search tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and act upon data found in local files such as '.radar/ROUTES.md', '.radar/SYMBOLS.md', and 'MAP.md', which could be controlled by an external actor in a repository.\n
  • Ingestion points: The agent is instructed to check and process content from '.radar/ROUTES.md', '.radar/SYMBOLS.md', and 'MAP.md'.\n
  • Boundary markers: There are no explicit markers or instructions to treat the content of these files as untrusted data.\n
  • Capability inventory: The agent has the ability to execute 'radar' commands and perform file system searches.\n
  • Sanitization: No sanitization or validation logic is specified for the content ingested from the repository files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 07:26 AM
Security Audit — agent-trust-hub — radar-navigation