skill-content-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon data from external and untrusted sources, including competitor account details, hotlist APIs, and user profiles, which serves as a potential vector for malicious instructions.
- Ingestion points: Untrusted data enters the context during Phase 0 (Account Profile) and Phase 2 (Competitor content analysis and Hotlist API research).
- Boundary markers: The instructions do not provide explicit delimiters or instructions to the agent to ignore potentially malicious content embedded within these data sources.
- Capability inventory: The skill possesses the ability to execute shell commands (via Python scripts) and write files to the local directory, which could be leveraged if an injection is successful.
- Sanitization: The skill does not describe any sanitization, validation, or filtering of the content retrieved from external research phases.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a specific shell command (
python skills/shared/scripts/calendar_ops.py context --days 14) to retrieve the current state of the content calendar. While this is an intended feature for coordination between skills, it involves direct interaction with the host's command line.
Audit Metadata