cli-contexts
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill documentation instructs the agent to install the 'omniroute' package from the NPM registry using the command 'npm install -g omniroute'.
- [COMMAND_EXECUTION]: The skill facilitates the execution of various CLI subcommands through the 'omniroute' binary to manage and inspect context engineering pipelines.
- [CREDENTIALS_UNSAFE]: The tool's design involves handling sensitive information in potentially unsafe ways:
- The 'contexts add' command uses flags like '--api-key' and '--access-token', which requires the agent to handle and pass credentials in plaintext.
- The 'contexts export' command defaults to including secrets in the exported JSON file unless the '--no-secrets' flag is specifically invoked.
- The 'contexts migrate' command references the existence of legacy plaintext credentials on the filesystem.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where malicious instructions could be ingested from external sources:
- Ingestion points: External content is brought into the environment via 'contexts import ' and 'sessions show ' (SKILL.md).
- Boundary markers: The documentation does not provide instructions for using boundary markers or markers to ignore instructions within the imported data.
- Capability inventory: The tool allows modifying context settings, exporting files, and executing shell commands (SKILL.md).
- Sanitization: There is no description of filtering or sanitizing the data imported from external session logs or context files.
Audit Metadata