openspec-brownfield-baseline
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill executes
npx @fission-ai/openspec@latestto download and run the validation tool from the package registry. - [COMMAND_EXECUTION]: Shell commands are invoked to initialize the OpenSpec folder structure and to perform structural validation of specification files.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a broad ingestion surface as it analyzes external codebase artifacts (source, tests, docs) to derive behavior, which presents a surface for indirect prompt injection. 1. Ingestion points: Reads from controllers, handlers, schemas, integration tests, logs, and telemetry (SKILL.md, Step 3). 2. Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted codebase content from the agent's instructions. 3. Capability inventory: The skill performs file writes to the local filesystem and executes shell commands for validation (SKILL.md, Steps 5 and 8). 4. Sanitization: There are no explicit instructions to sanitize or validate the content of the ingested files before processing.
Audit Metadata