groom-jira
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from JIRA which could theoretically contain malicious instructions.
- Ingestion points: JIRA issue fields (such as summaries and comments) are fetched using
mcp_jira_searchJiraIssuesUsingJqlin various grooming steps inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are provided to distinguish between JIRA data and the skill's own instructions.
- Capability inventory: The agent has the authority to edit, transition, and comment on JIRA issues based on the ingested data.
- Sanitization: There is no explicit mechanism for sanitizing or validating the content retrieved from JIRA.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command to monitor policy freshness.
- Evidence:
SKILL.mdspecifies the use ofgit log -1 --format="%ai"to check the last-modified date of the skill file. - Note: This is a read-only command used for governance compliance and is not inherently malicious.
Audit Metadata