user-activity-report
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from various external platforms to build its reports. This creates an attack surface where instructions embedded in pull request titles, Slack messages, or documentation could attempt to influence the agent's behavior.
- Ingestion points: The skill ingests data from the
personargument and content retrieved from GitHub PRs, Slack threads, Jira tickets, and Confluence pages (SKILL.md). - Boundary markers: There are no explicit instructions to use delimiters or to disregard instructions found within the retrieved data.
- Capability inventory: The skill executes
gh apicommands and performs network-based searches across multiple internal and external data sources (SKILL.md). - Sanitization: No sanitization or filtering of the retrieved data is mentioned before it is synthesized by the LLM.
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh api) to programmatically fetch activity data. These commands are constructed using variables (like organization and repository names) resolved during the identity resolution and search phases.
Audit Metadata