writing-manual-test-cases
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Jira tickets, Confluence requirements, and GitHub Pull Requests, creating a potential surface for indirect prompt injection.
- Ingestion points: External data is ingested via the
bitwarden-atlassian-toolsskill and GitHub CLI commands (gh pr view,gh pr diff). - Boundary markers: The instructions include a specific defensive directive to treat all ingested content as untrusted data rather than instructions, explicitly citing CWE-1427 and instructing the agent to ignore imperative text.
- Capability inventory: The skill is authorized to write test case files (
Write) to a plugin-specific data directory and execute scoped GitHub CLI commands via Bash. - Sanitization: The skill relies on prompt-based isolation to prevent malicious instructions in the source data from influencing agent behavior.
Audit Metadata