teambition-ego
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and displays external data (test case titles, preconditions, and steps) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is fetched from the Teambition API in
scripts/lib/domains/testcase.mjsvia thecollectCasesandfindCasefunctions. - Capability inventory: The skill possesses write capabilities including creating, updating, and archiving test cases (defined in
scripts/lib/domains/testcase.mjs), which could be misdirected by injected instructions. - Sanitization: External content is formatted for display using standard string templates in
scripts/lib/pure.mjsbut is not specifically sanitized to neutralize potential prompt injection commands. - Boundary markers: The skill does not use specific delimiters or 'ignore embedded instructions' warnings when presenting external test case data to the agent.
Audit Metadata