skills/sehoon787/my-claude/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands using npm, git, and gh to perform release tasks like testing, tagging, and publishing to external registries.
  • [PROMPT_INJECTION]: The skill accepts user-provided arguments (<version>, <title>, <release notes>) which are directly interpolated into shell commands. This creates an indirect prompt injection surface where a malicious input could potentially lead to command injection or unintended shell behavior.
  • Ingestion points: User-provided <version>, <title>, and <release notes> arguments.
  • Boundary markers: None present to delimit user input or instruct the agent to treat them as literal data.
  • Capability inventory: Executes npm run test:run, git commit, git tag, git push, npm publish, and gh release create via shell.
  • Sanitization: No explicit sanitization or validation of the input arguments is defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:43 AM
Security Audit — agent-trust-hub — release