spec-testability-heuristics
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary text from user stories, PRDs, and feature specifications to score them against testability heuristics. This processing of untrusted data creates a surface for indirect prompt injection.
- Ingestion points: The workflow identifies several intake sources, including Jira/Linear tickets, design document sections, and markdown feature specifications.
- Boundary markers: The instructions command the agent to tokenize text into claims but do not define specific security delimiters or provide instructions to ignore potential commands embedded within the analyzed text.
- Capability inventory: The skill's primary function is text analysis and the generation of markdown reports. It lacks access to sensitive file paths, network resources, or administrative command execution.
- Sanitization: No explicit sanitization or filtering of the input text is performed before the content is evaluated against the heuristics.
Audit Metadata