release-notes-generator
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external ticketing systems that could contain malicious instructions targeting the agent.
- Ingestion points: Data is pulled from external sources specified in the
{{TICKET_SOURCES}}placeholder (Linear, Jira, or GitHub Issues) as described inSKILL.md. - Boundary markers: The prompt template lacks explicit delimiters or instructions for the agent to ignore any embedded commands within the ticket descriptions.
- Capability inventory: The skill has the capability to write files to Google Drive using the required Google Drive MCP.
- Sanitization: There is no evidence of content validation or sanitization before the external ticket data is interpolated into the prompt and processed.
Audit Metadata