repo-activity
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes 'git remote -v' to determine the current repository and 'gh api' to fetch data from GitHub. These are standard operations for the skill's purpose but involve direct command-line interaction.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of untrusted external data.
- Ingestion points: Data is fetched via the GitHub API, including issue descriptions and pull request comments.
- Boundary markers: The implementation lacks explicit delimiters or instructions to the agent to ignore embedded commands within the fetched content.
- Capability inventory: The agent has the ability to execute commands through the 'gh' CLI and write report files to the local system.
- Sanitization: There is no evidence of sanitization or validation of the retrieved text before it is processed for summaries.
Audit Metadata