jira-issue-to-pr
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The automation script
scripts/main.pyprocesses untrusted data from Jira and interpolates it directly into agent prompts, creating a surface for indirect prompt injection. - Ingestion points: The
summaryanddescriptionfields from Jira Cloud issues are fetched and used to build the initial message for the spawned agent conversation inscripts/main.py. - Boundary markers: There are no explicit boundary markers (e.g., XML tags or clear delimiters) or instructions to ignore embedded commands used when interpolating the Jira issue content into the prompt.
- Capability inventory: The agent conversations started by this skill have the capability to clone repositories, modify code, commit changes, and push to remote branches on GitHub, GitLab, or Bitbucket.
- Sanitization: The script performs ADF (Atlassian Document Format) to plain-text extraction using
extract_adf_textinscripts/main.py, but it does not perform any escaping, filtering, or validation of the resulting text before prompt interpolation.
Audit Metadata