rust-readme
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for documentation generation and follows established best practices for repository management. It includes explicit directives to avoid including sensitive information like credentials or private tokens in public-facing documentation. All external references point to legitimate and well-known developer resources and documentation hosts.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository (e.g., Cargo.toml, CI configurations, and source code) to extract metadata for README generation, which represents a potential attack surface.\n
- Ingestion points: Files processed include package manifests, build configurations, and code examples residing within the target repository.\n
- Boundary markers: Not explicitly utilized during the information gathering phase.\n
- Capability inventory: The skill is limited to file system read access and writing to README files; it does not possess the capability to execute code or initiate network connections.\n
- Sanitization: The agent is tasked with verifying the validity of the data it finds, though no formal sanitization process for the ingested strings is specified.
Audit Metadata