emergency-response

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface. The skill is designed to ingest and analyze untrusted external data (entire codebases) which could contain malicious instructions designed to subvert the agent's behavior.
  • Ingestion points: Reads the codebase, project configurations, and external system integration maps (Step 1.1, Step 1.3).
  • Boundary markers: None defined. There are no instructions to use delimiters or ignore embedded instructions in the analyzed files.
  • Capability inventory: Extensive local file system read access across the project directory.
  • Sanitization: No sanitization, escaping, or validation of the ingested code content is performed before processing.
  • [COMMAND_EXECUTION]: The skill performs local file system writes for telemetry purposes. It attempts to append execution metadata to ~/.claude/projects/.../skill-telemetry.md. While this is localized to the tool's own configuration directory, it represents a write operation outside the immediate working project path.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:56 AM
Security Audit — agent-trust-hub — emergency-response