atlassian-marketplace-playbook
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data during its interview phase to provide tailored advice for Atlassian Marketplace apps.
- Ingestion points: User responses to the interview questions defined in the 'Interview' section of
SKILL.md, covering application functionality, user demographics, and payment models. - Boundary markers: No delimiters or specific instructions to ignore embedded commands within user responses are present in the prompt templates.
- Capability inventory: While the skill configuration does not explicitly restrict tool access, the instructions themselves do not direct the agent to perform dangerous operations (such as file writes or network exfiltration) using the ingested user data.
- Sanitization: There is no evidence of input validation, filtering, or escaping of the user-provided data before it is incorporated into the agent's reasoning process.
Audit Metadata