calendar-to-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted calendar data from external sources which could be used to influence agent behavior. * Ingestion points: The skill reads .ics files from the filesystem or processes raw iCal content provided by the user. * Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within the calendar data. * Capability inventory: The skill has permissions to write files, edit content, and change file permissions via chmod, allowing it to create executable scripts. * Sanitization: The instructions do not specify any validation or sanitization of the calendar event content before it is used to generate documents or scripts.
- [DYNAMIC_EXECUTION]: The skill generates shell scripts based on calendar data and repository context. * Evidence: The skill generates recurring workflow scripts and is granted Bash(chmod:*) permissions to make these generated scripts executable.
- [COMMAND_EXECUTION]: The skill executes Git and GitHub CLI commands to retrieve repository activity. * Evidence: Uses git log to gather recent commits and gh pr list / gh run list to check pull requests and CI status.
Audit Metadata