skills/jschulte/stackshift/implement/Gen Agent Trust Hub

implement

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Command Execution] (LOW): The skill generates and executes shell scripts to automate git branch creation and file initialization (Step 5). This falls under simple script generation from known templates, which is a standard but low-risk operation.
  • [Indirect Prompt Injection] (LOW): The skill defines a surface where untrusted data from implementation plans is used to populate variables in shell commands.
  • Ingestion points: Data is read from files within .specify/memory/plans/ as described in operations/handoff.md.
  • Boundary markers: Absent; the skill does not specify delimiters or warnings to ignore instructions embedded within the plan files.
  • Capability inventory: The skill utilizes shell command execution (git, cat) within the handoff.md procedure.
  • Sanitization: Absent; there is no explicit validation or escaping of the FEATURE_NAME variable before it is used in command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 05:42 AM