graph-blast-radius

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script (.claude/scripts/code_graph) for various tasks like calculating blast radius, tracing dependencies, and querying the code graph. This is the primary functional mechanism of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository (specifically filenames and git changes) and interpolates them into bash command strings.
  • Ingestion points: Filenames and class/function names derived from the local source code and git diffs.
  • Boundary markers: None present; values are directly interpolated into command lines.
  • Capability inventory: The skill has access to the Bash tool, enabling arbitrary command execution on the host system.
  • Sanitization: There is no explicit instruction to sanitize or escape these identifiers before they are passed to the shell, which could lead to command injection if a file is maliciously named (e.g., ; rm -rf / .js).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:24 AM
Security Audit — agent-trust-hub — graph-blast-radius