skills/gracdjd/skills/sdd-slim-review/Gen Agent Trust Hub

sdd-slim-review

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external files.
  • Ingestion points: Processes source code files, diffs, build outputs, and spec documents.
  • Boundary markers: No explicit security delimiters or ignore-instructions warnings are used when reading external content.
  • Capability inventory: Restricted to reading files and writing to Markdown spec files; it explicitly lacks shell execution, network access, or code modification capabilities.
  • Sanitization: No evidence of input validation or content filtering is present in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 02:37 PM