make-it-hireable

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and processes project files (README, manifests, source code) to perform audits and implement changes. This untrusted data could contain malicious instructions that influence the agent's actions during the audit or execution phases.\n
  • Ingestion points: SKILL.md section 1 specifies reading manifests, entry points, config, and README files.\n
  • Boundary markers: No explicit markers are used to separate user data from agent instructions.\n
  • Capability inventory: The agent can write files, create git branches, and execute shell commands.\n
  • Sanitization: No sanitization or validation steps are defined for the ingested project content.\n- [DYNAMIC_EXECUTION]: The agent is instructed to verify changes by executing the project's own build scripts and test suites.\n
  • Evidence: SKILL.md section 2.2 requires the agent to "run the tests, build, lint, and start the app if feasible."\n- [COMMAND_EXECUTION]: The skill utilizes shell commands for repository management.\n
  • Evidence: Uses git for status checks, initialization, and branch/commit operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 06:30 AM