lld-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script
python3 plugins/testany-eng/scripts/trace_lint.pyto validate metadata consistency. This script is a vendor-owned resource belonging to the 'testany-io' infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources such as PRD, HLD, and API Contract files.
- Ingestion points: Project documents scanned and read during Phase 0, including PRD, HLD, Contract, Guardrails, and ADR files.
- Boundary markers: The instructions lack explicit delimiters or safety prompts to ensure the agent ignores embedded instructions within the source documents.
- Capability inventory: The skill performs local command execution (
python3) and file system write operations for document generation. - Sanitization: No filtering or sanitization mechanisms are described for the content ingested from the external project documents.
Audit Metadata