search-cluster-creators-guide
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves article content and search results from
https://creator.cluster.mu/. Thefetch_article.pyscript validates that URLs start with this domain before making a network request.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML content from an external website which is then passed to the agent.\n - Ingestion points: HTML content is fetched and parsed in
scripts/fetch_article.pyandscripts/search.py.\n - Boundary markers: The skill does not use specific delimiters or instructions to ignore content within the fetched data.\n
- Capability inventory: The skill is limited to reading and parsing information; it does not have the ability to write files, execute arbitrary shell commands, or access sensitive local data.\n
- Sanitization: The scripts use the standard
html.parser.HTMLParserlibrary to extract text and structural elements, stripping out scripts and other executable content from the fetched HTML.
Audit Metadata