verifying-doc-parity
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources and pull request metadata, which then influences its file-writing behavior.
- Ingestion points: The skill reads pull request diffs, descriptions, and content from
contributing.bitwarden.com(as described in SKILL.md under 'Workflow' and 'Out-of-repo discovery'). - Boundary markers: There are no explicit instructions or markers mentioned to prevent the agent from following malicious instructions embedded within the code diffs or external documentation.
- Capability inventory: The skill utilizes the
Edittool to modify documentation files based on the analyzed drift (SKILL.md Step 3). - Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the data ingested from external sources or diffs.
Audit Metadata