jira-markdown-conversion
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Jira issues which could contain malicious instructions designed to influence the agent's behavior during the conversion process.
- Ingestion points: Data is fetched via
mcp__atlassian__getJiraIssueandmcp__atlassian__searchJiraIssuesUsingJql(referenced inSKILL.md). - Boundary markers: None identified. The skill instructions do not provide delimiters or warnings to the agent to ignore instructions embedded within the Jira fields (description, comments).
- Capability inventory: The skill is allowed to use the
Writetool, allowing the agent to save potentially poisoned output to the local file system. - Sanitization: No evidence of sanitization or filtering of the ingested Jira content before Markdown transformation.
- [DATA_EXPOSURE]: The skill includes a hardcoded Atlassian Cloud ID (
f6e0f50a-4acf-4011-90fa-8fcc9b50cd86) for the instancehadron.atlassian.net. While this is a unique identifier and not a secret credential (like an API key), it hardcodes the skill to a specific target environment.
Audit Metadata