cli-anything-renderdoc
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the "cli-anything-renderdoc" Python package from a public registry, which is the official package for this tool.
- [COMMAND_EXECUTION]: The skill defines a set of commands for interacting with the local filesystem to read graphics capture files (".rdc") and export analysis results such as textures, shaders, and metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted binary graphics captures. Information extracted from these files, such as shader source code or action summaries, is intended for ingestion by the agent.
- Ingestion points: Various commands process external ".rdc" files to extract metadata, shader source, and resource details (e.g., in SKILL.md).
- Boundary markers: The skill does not explicitly describe the use of boundary markers or delimiters for the output generated from external captures.
- Capability inventory: The skill possesses the ability to read binary captures and write files (textures, shaders, JSON reports) to the local disk.
- Sanitization: The skill relies on the RenderDoc API's parsing of the binary capture format.
Audit Metadata