specify
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external and project-based sources to synthesize documentation.
- Ingestion points: The skill fetches and reads content from
AGENTS.md, local project files (glossary, requirements, code, backlog), and referenced remote records (including bodies and comments of tasks). - Boundary markers: The instructions do not define any specific boundary markers or delimiters to differentiate between system instructions and data from ingested files or remote records.
- Capability inventory: The skill has file-writing capabilities across the repository, including the ability to create and update specifications, requirements, changelogs, and the project backlog.
- Sanitization: There is no mention of sanitizing, escaping, or validating the content retrieved from remote sources or existing files before it is processed or written back to the repository.
Audit Metadata