writing-a-readme
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from untrusted project files to populate README templates, which is a potential vector for indirect prompt injection.
- Ingestion points: SKILL.md (Step 2) identifies files such as package.json, pyproject.toml, Cargo.toml, go.mod, LICENSE, and CONTRIBUTING.md as data sources.
- Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore any embedded commands or formatting within the ingested files.
- Capability inventory: The skill's functions are limited to text processing and markdown generation. It does not perform network operations, execute shell commands, or modify sensitive system files.
- Sanitization: There is no evidence of content validation or escaping for the data read from project files before it is interpolated into the README structure.
Audit Metadata