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 in SKILL.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
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — release-notes-generator