skills/jeremylongshore/tons-of-skills-marketplace/creating-github-issues-from-web-research/Gen Agent Trust Hub
creating-github-issues-from-web-research
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external web sources via search and fetch tools, which could contain malicious instructions designed to manipulate the agent's behavior or the content of created issues.
- Ingestion points: Web search results and fetched webpage content retrieved using the
WebSearchandWebFetchtools. - Boundary markers: The skill uses markdown templates (
assets/issue_template.md) and configuration placeholders ({{summary}},{{url}}) to structure external data, providing a basic layer of separation. - Capability inventory: The skill has access to
Read,WebFetch,WebSearch, andGreptools, and it utilizes custom Python scripts (github_issue_creator.py) to interact with the GitHub API. - Sanitization: The
assets/config_template.jsonfile defines security settings includingsanitize_htmlandallowed_domains, which are best-practice mitigations for handling untrusted content.
Audit Metadata