tasks-explain-diff
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted code content to generate summaries and documentation.
- Ingestion points: The skill reads code changes pointed to by the user or extracted from the recent conversation history in
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its operational rules and the content of the code changes being analyzed.
- Capability inventory: The skill has the capability to write data to external Notion pages using the Notion MCP tool.
- Sanitization: No validation, sanitization, or filtering of the input code is performed before it is used to generate the Notion document.
Audit Metadata