learn-pr-learnt
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub PR reviews and saves it into the agent's instructional files, creating a vulnerability to indirect prompt injection.\n
- Ingestion points: The skill ingests PR comments, review bodies, and discussion threads using
gh apicalls in SKILL.md.\n - Boundary markers: Absent. The instructions do not specify boundary markers or include warnings to ignore instructions embedded in the comments.\n
- Capability inventory: The agent can write extracted data to project-specific files (
MEMORY.md,AGENTS.md) and global configuration files (~/.agents/skills/).\n - Sanitization: Absent. No logic is provided to sanitize or validate the content before it is stored as a persistent instruction.\n- [COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI (
gh) to search pull requests and fetch API data, and uses thedateutility to calculate time ranges.
Audit Metadata