forge-app-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves the latest Forge connector best practices and manifest references from Atlassian's official developer documentation (developer.atlassian.com) using the
read_url_contenttool to ensure reviews are based on current platform requirements. - [INDIRECT_PROMPT_INJECTION]: Because the skill is designed to ingest and analyze untrusted source code and configuration files, it presents a surface for indirect prompt injection where adversarial content in the reviewed files could attempt to influence the agent's findings.
- Ingestion points: Local project files including
manifest.yml,package.json, and application source files (.js, .jsx, .ts, .tsx), in addition to external documentation content. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the code being analyzed.
- Capability inventory: The skill utilizes file system read access and the
read_url_contenttool to aggregate information for generating a readiness report. - Sanitization: There is no evidence of content sanitization or validation of the source code before it is interpreted by the agent for the review process.
Audit Metadata