spec-kit-specify

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (HIGH): High risk of indirect prompt injection as untrusted user input is used to drive critical execution steps and document generation without sanitization or boundary markers. 1. Ingestion point: Step 01 ('Treat the full user request as the feature description'). 2. Boundary markers: Absent. 3. Capability inventory: Execution of 'create-new-feature.sh' and multiple file write operations. 4. Sanitization: Absent.
  • COMMAND_EXECUTION (HIGH): In Step 03, the user-provided feature description is passed directly as a command-line argument to 'scripts/create-new-feature.sh'. This pattern is highly susceptible to shell command injection if the user request contains shell metacharacters.
  • COMMAND_EXECUTION (MEDIUM): The skill executes shell scripts using relative paths ('../../spec-kit/scripts/') to access resources outside the skill's own package, creating a dependency on the external file system layout that could be exploited in less isolated environments.
Recommendations
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 09:26 AM