writing-stickiness

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user content to perform its core functions.
  • Ingestion points: The skill reads entire user-provided drafts in Step 1.1 of the workflow defined in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the processed draft.
  • Capability inventory: The skill is instructed to create, write, and read a local analysis file (writer-stickiness-analysis.md) to manage its multi-step refinement process.
  • Sanitization: No input validation or sanitization of the user-provided draft is performed before the agent analyzes and acts upon it.
  • [NO_CODE]: The skill does not contain any executable scripts, binaries, or shell commands, consisting entirely of Markdown-based instructions and a JSON evaluation rubric.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 05:10 PM