ctxora-context-health
Warn
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx ctxorato fetch and execute code from the npm registry at runtime. This package is not from a known trusted organization or vendor. - [COMMAND_EXECUTION]: The skill executes multiple shell commands to run diagnostics (
doctor,status), calculate context health (context-score), repair state (repair), and run CI checks (ci). These operations interact with the local file system and repository state. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests data from a repository workspace specified via the
<repository>parameter inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters telling the agent to ignore or isolate commands/instructions that might be found within the repository's files.
- Capability inventory: The tool has the capability to write to the
.ctxora/directory and execute CI workflows, which could be triggered by malicious content in a repository. - Sanitization: There is no evidence of sanitization or validation of the repository content before it is processed by the diagnostic or indexing tools.
Audit Metadata