speckit-phasestoissues

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts and git commands to establish project context. Specifically, it sources '.specify/scripts/bash/common.sh' and performs file modifications using 'echo' and 'git commit' in Step 7.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of local project files. 1. Ingestion points: Reads 'spec.md', 'tasks.md', and 'plan.md' in Step 3. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when content is interpolated into the issue body. 3. Capability inventory: Local script execution and GitHub API access via MCP. 4. Sanitization: No evidence of input validation or escaping of the ingested markdown content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:47 PM