interview-coach

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts within its root directory, such as scaffold-state.mjs and profile-strength.mjs, to initialize the environment and calculate profile metrics.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external job postings and company websites to generate prep briefs and questions.
  • Ingestion points: Job posting content (URLs or pasted text) and company research data from web browsing are incorporated into the agent's context in SKILL.md Steps 1 and 2.
  • Boundary markers: None identified; external content is parsed and used directly to generate interview questions and talking points.
  • Capability inventory: The skill has the ability to execute shell commands via node and perform file system read/write operations within the user's document directory.
  • Sanitization: No evidence of sanitization or filtering of external job posting content or web research results before they are processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 02:29 PM
Security Audit — agent-trust-hub — interview-coach