build-and-release
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-provided data from the
$ARGUMENTSvariable directly into a task description for build and release subagents.\n- Ingestion points:SKILL.md(via$ARGUMENTS).\n- Boundary markers: None; the input is not enclosed in delimiters (e.g., XML tags or code blocks) or accompanied by instructions to ignore embedded commands.\n- Capability inventory: The skill orchestratesbuildandreleaseworkflows, which typically involve significant capabilities such as file system writes, shell command execution, and network access for deployment.\n- Sanitization: None; there is no evidence of validation or filtering for the user-supplied input.
Audit Metadata