speckit-analyze

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The scripts/check-prerequisites.sh script employs eval $(get_feature_paths). The get_feature_paths function in scripts/common.sh generates shell assignments based on the current git branch or environment variables like SPECIFY_FEATURE. While variables are single-quoted, this pattern remains a minor risk if an attacker can manipulate the git environment to include single quotes in branch names, potentially leading to command breakout.
  • [PROMPT_INJECTION] (LOW): Category 8: Indirect Prompt Injection. The skill ingests untrusted data from project artifacts.
  • Ingestion points: spec.md, plan.md, and tasks.md (Step 2 in SKILL.md).
  • Boundary markers: Absent; the skill does not define delimiters to wrap external artifact content.
  • Capability inventory: The skill uses subprocess execution for prerequisites and possesses read-only file access; no network or file-write capabilities are defined.
  • Sanitization: No sanitization or validation of the content of the analyzed files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 10:56 PM