tdd-plan
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a read-only directory listing command (
ls -t docs/cycles/*.md) to locate the most recent cycle documentation. This is a standard and safe operational procedure. - [EXTERNAL_DOWNLOADS]: The skill utilizes platform-native
WebSearchandWebFetchcapabilities to verify library versions and documentation during implementation planning. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. Ingestion points: Data from WebSearch and WebFetch tools (SKILL.md). Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands in the external data. Capability inventory: Execution of shell commands (
ls) and invocation of thetdd-core:plan-reviewskill. Sanitization: Absent; the skill does not specify any filtering or validation for retrieved external content.
Audit Metadata