skills/tanabee/skills/create-pr-text/Gen Agent Trust Hub

create-pr-text

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues and local project files to generate pull request text, which could contain adversarial instructions targeting the agent.
  • Ingestion points: The skill uses the gh issue view command to fetch external content from GitHub. It also reads local files like plan.md, report.md, and implementation-notes.md in SKILL.md step 2.
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the external issue content or warn the agent to ignore instructions embedded within the fetched text.
  • Capability inventory: The skill is granted access to the Bash, Write, Read, Glob, and Grep tools. This allows the agent to execute shell commands and modify the local filesystem based on the processed data.
  • Sanitization: The instructions do not specify any validation, escaping, or filtering for the external content before it is processed or written to pr.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 05:08 AM
Security Audit — agent-trust-hub — create-pr-text