watch-run
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
covalCLI tool to list, watch, and retrieve run data. This tool is a resource provided by the vendor (coval-ai) and its use is consistent with the skill's stated purpose of monitoring runs. - [INDIRECT_PROMPT_INJECTION]: The skill processes output from external shell commands, which creates a potential surface for indirect prompt injection if the output contains untrusted data.
- Ingestion points: Data is ingested from the output of
coval runs list,coval runs watch, andcoval runs getas described in Step 1, Step 2, and Step 3 of the workflow in SKILL.md. - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the CLI output.
- Capability inventory: The skill has the capability to execute shell commands using the
covalCLI (SKILL.md). - Sanitization: There is no explicit sanitization or validation of the content returned by the CLI tools before the agent processes and summarizes it for the user.
Audit Metadata