jira
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell scripts (
scripts/download-attachment.sh,scripts/md-to-adf.py) and theacliCLI tool to interact with Jira services. These commands are used for legitimate task management workflows. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically Jira issue fields (summaries, descriptions, comments) and attachments.
- Ingestion points: Data enters the agent context through
acli jira workitem viewandacli jira workitem searchcommands as documented inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts were found in the skill's instructions.
- Capability inventory: The skill has the ability to execute shell commands (via
acli), perform file writes (viacurl -oinscripts/download-attachment.sh), and write data back to Jira (create/edit/comment/transition). - Sanitization: No sanitization or filtering of the ingested Jira content was observed before it is processed by the agent.
Audit Metadata