clockify
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides various shell commands using
curlto query and update the Clockify API and look up issue details on a Jira instance. - [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content from Jira issue summaries into Clockify time entry descriptions, which could be exploited if an attacker controls a Jira issue title.
- Ingestion points: Fetches issue keys and summaries from the Jira REST API via
$JIRA_SITE/rest/api/3/issue/{key}and search endpoints as documented inSKILL.md. - Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between its instructions and the data fetched from Jira.
- Capability inventory: The skill has the capability to write to the Clockify API using
curl -X POSTandcurl -X PUTrequests, effectively exfiltrating or modifying tracking data based on processed input. - Sanitization: There is no evidence of sanitization, filtering, or validation of the Jira issue summary before it is used to construct the Clockify entry description.
Audit Metadata