skills/ahgraber/skills/sdd-apply/Gen Agent Trust Hub

sdd-apply

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to implement and test code, which involves the execution of shell commands and scripts to fulfill development tasks.
  • [PROMPT_INJECTION]: The skill processes untrusted content from local project files (e.g., tasks.md, design.md), creating a surface for indirect prompt injection where documentation content could influence agent actions.
  • Ingestion points: Files within the .specs/ directory are loaded as implementation context in SKILL.md.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat documentation content as data rather than instructions.
  • Capability inventory: The agent is authorized to write files and execute commands (COMMAND_EXECUTION).
  • Sanitization: No validation or filtering of the content read from the documentation files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 12:44 PM