testsprite-ai-testing-cli
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill manages authentication tokens (
TESTSPRITE_API_KEY) and stores them in a local credentials file at~/.testsprite/credentials. While this is a standard pattern for developer CLI tools, the file represents a sensitive target for credential exposure. - [EXTERNAL_DOWNLOADS]: The skill triggers the installation of the
@testsprite/testsprite-clipackage from the NPM registry. It also downloads test artifacts including screenshots, DOM snapshots, and generated TypeScript source code (test-source.ts) from the TestSprite platform during failure analysis. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from the TestSprite API that contains natural language instructions intended to influence the agent's behavior.
- Ingestion points: The
failure.jsonfile, specifically therootCauseHypothesisandsuggestedFixfields, which are downloaded using thetestsprite test failure getcommand. - Boundary markers: No explicit boundary markers or warnings are used to instruct the agent to ignore potentially malicious instructions embedded in the API responses.
- Capability inventory: The agent utilizing this skill has the capability to write to the local filesystem, modify application source code, and execute shell commands to run/rerun tests.
- Sanitization: There is no evidence of sanitization or validation of the suggested fixes provided by the remote API before the agent is prompted to act upon them.
Audit Metadata