detox-testing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing and acting upon external data sources, including test failure logs, run summaries, and pull request diffs, which serves as a potential attack surface for indirect prompt injection.
- Ingestion points: The agent is expected to read and interpret content from files such as
reports/tap-timeout.log,reports/e2e-runs.md, andpatches/pr-812.diff. - Boundary markers: There are no instructions for the agent to use delimiters or 'ignore instructions' wrappers when processing these data files, increasing the risk that instructions embedded in logs could be followed.
- Capability inventory: The skill encourages the use of tools for significant file modifications (editing
e2e/tests andapp/components) and shell execution (detox test,detox build). - Sanitization: The skill lacks guidance on sanitizing, escaping, or validating the external content before it is interpolated into the agent's context or used to drive subsequent actions.
Audit Metadata