qa-agent
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process external data from Jira tasks and feature requests, creating a potential vector for malicious instructions to be introduced via task descriptions.
- Ingestion points: Jira tasks and user requests described in SKILL.md.
- Boundary markers: Absent; no specific delimiters are defined to isolate external data from instructions.
- Capability inventory: Mentions the use of browser and simulator tools to interact with features.
- Sanitization: Absent; no validation or sanitization process for the input task content is specified.
- [NO_CODE]: The skill is composed entirely of markdown instructions and YAML metadata. It does not include any scripts, source code, or configuration files for package managers.
Audit Metadata