setting-up-a-project
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the local repository to determine the project setup status and to perform specification graph extensions.\n
- Ingestion points: Uses workspace tools
spec_grepandspec_graphto read existing project files, source code, and documentation likegoal-and-requirements.mdorSPEC.md.\n - Boundary markers: There are no explicit instructions to the agent to treat content from these files as data rather than instructions, nor are there delimiters to prevent embedded prompts from influencing the agent's behavior.\n
- Capability inventory: The agent is instructed to analyze code, draft specification graphs, and route the workflow to other skills such as
importing-a-codebaseorstarting-a-new-project.\n - Sanitization: The instructions do not mention any sanitization, escaping, or validation of the content retrieved from the workspace files before it is processed by the LLM.
Audit Metadata