Skills
skills/team-attention/notion-skills-for-claude/notion-spec-to-implementation/Gen Agent Trust Hub

notion-spec-to-implementation

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to fetch arbitrary content from Notion specification pages via Notion:notion-fetch and act on that data to create plans and tasks. A malicious specification page could contain hidden instructions intended to divert the agent's behavior. Ingestion points: Notion:notion-fetch used in SKILL.md and reference/spec-parsing.md to retrieve specification content. Boundary markers: None. The instructions do not define delimiters or warnings to ignore instructions embedded within the spec content. Capability inventory: The skill uses Notion:notion-create-pages and Notion:notion-update-page, allowing the agent to modify the Notion environment based on the input data. Sanitization: No validation or filtering logic is prescribed for the retrieved content.
  • [NO_CODE]: The skill consists entirely of Markdown-based guidance, templates, and evaluation JSON files. No executable scripts in Python, JavaScript, or Bash are provided within the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 10:47 PM