dsh-go-support
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process diagnostic files (
diagnostics.md,diagnostics-manual.md), which are external data sources that could be manipulated to include malicious instructions targeting the agent. - Ingestion points: The agent is instructed to read local files located at
$DSH_HOME/dsh-app/diagnostics.mdand$DSH_HOME/dsh-app/diagnostics-manual.md. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the diagnostic content.
- Capability inventory: The agent has the capability to read local files, process their content, and generate formatted text output (issue drafts) for the user.
- Sanitization: There is no evidence of content sanitization or validation for the data read from the diagnostic files.
- [COMMAND_EXECUTION]: The skill provides the agent with specific shell-style directives and file paths to perform read operations on the local file system to retrieve application snapshots and logs.
Audit Metadata