release-notes

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes and instructs the user to run a local Python script (scripts/release_notes_generator.py) to process structured release data. This script performs file reading and text formatting based on user-provided JSON input.\n- [PROMPT_INJECTION]: The skill is designed to process technical entries gathered from external, untrusted sources which exposes the agent to indirect prompt injection.\n
  • Ingestion points: Technical changes gathered from Jira, Linear, Git logs, and PRD references (SKILL.md, Step 1) as well as the JSON file input for the generator script.\n
  • Boundary markers: There are no defined delimiters or specific instructions for the AI agent to ignore potentially malicious instructions embedded in the input data.\n
  • Capability inventory: The agent performs rewriting tasks on the data and interacts with a local script that can read files and output to the terminal.\n
  • Sanitization: The skill does not implement or recommend any sanitization or validation mechanisms to filter out instructional content from the technical logs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:08 AM