asa-roas-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow for ingesting data from external APIs (Apple Search Ads and RevenueCat) which creates a surface for indirect prompt injection.
  • Ingestion points: The agent receives untrusted external data via the 'asa_profitability', 'rc_overview', and 'rc_attribution_summary' tool outputs in SKILL.md.
  • Boundary markers: The skill instructions do not specify any delimiters or safety warnings to ensure the agent disregards instructions that might be embedded within the retrieved data.
  • Capability inventory: The skill utilizes tool execution for data retrieval and logic gating (such as 'asa_review_country_gate').
  • Sanitization: There are no provisions for filtering, escaping, or validating the integrity of the data returned by these external integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:19 PM
Security Audit — agent-trust-hub — asa-roas-analysis