parsing-changelogs
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's architecture for processing external changelogs creates a surface for indirect prompt injection (Category 8).
- Ingestion points: Untrusted external content is fetched from URLs defined in
metadata.feedUrl,metadata.markdownUrl, and HTML content scraped from various providers mentioned in the pipeline overview (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or "ignore embedded instructions" warnings when passing fetched content to the parsing logic, increasing the risk that embedded malicious commands could be obeyed.
- Capability inventory: The agent has access to management tools (
manage_source,manage_playbook), data retrieval tools (get_latest_releases,get_organization), and administrative CLI commands (releases admin source fetch,releases admin source update,releases admin source delete) (SKILL.md). - Sanitization: No sanitization or filtering of the fetched content is described before it is processed by the AI-driven parsing engine.
Audit Metadata