Skills
Navigate
skills/affitor/affiliate-skills/content-pillar-atomizer/Gen Agent Trust Hub

content-pillar-atomizer

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data via the pillar_content input, which can be provided as raw text or retrieved from a URL.
  • Ingestion points: pillar_content field in SKILL.md.
  • Boundary markers: Absent. The instructions do not define delimiters or specific 'ignore embedded instructions' prompts for the input text.
  • Capability inventory: The skill utilizes web_fetch (file/network access) and web_search (network access).
  • Sanitization: None. There is no evidence of input validation or escaping for the processed content.
  • [EXTERNAL_DOWNLOADS]: The skill employs web_fetch to retrieve content from remote URLs provided by the user and web_search to query for topic engagement data. These network operations target user-specified or search-driven external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 02:35 AM