readme-creator
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection because it ingests untrusted data from local project files without sanitization.
- Ingestion points:
SKILL.md(Phase 1) instructs the agent to read content frompackage.json,Cargo.toml,pyproject.toml,go.mod, and existingREADME.mdfiles. - Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the ingested project data from the agent's instructions.
- Capability inventory: The skill enables the agent to write files (README.md) and execute handoffs to other documentation skills (
docs-writing,agents-md). - Sanitization: No sanitization or validation logic is defined to prevent the execution of instructions that might be contained within project metadata fields like descriptions or scripts.
Audit Metadata