cali-product-opportunity-mapping

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its handling of user-provided data.
  • Ingestion points: Untrusted data enters the agent's context through the <USER INPUT> placeholder in SKILL.md during the prompt generation process.
  • Boundary markers: The skill uses XML-style tags (<USER INPUT>) to delimit user data, which provides basic structural separation but does not include explicit instructions for the model to ignore any embedded commands within that input.
  • Capability inventory: The skill's capabilities are highly restricted. It does not perform network operations, file system modifications, or command execution. Its output is limited to generating text in Confluence Wiki Markup format.
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the content provided by the user before it is interpolated into the final prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 09:01 AM
Security Audit — agent-trust-hub — cali-product-opportunity-mapping