devrel-content-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data, such as a user's existing project documentation, audience profiles, and program strategies. This ingestion surface is susceptible to indirect prompt injection if the processed files contain malicious instructions. The impact is low because the skill lacks executable capabilities or file-write permissions.
- Ingestion points: The workflow involves reading user-provided strategy files and audience profiles during the initial planning phase (SKILL.md).
- Boundary markers: The instructions enforce a highly structured output format (five-section plan with specific tables), which acts as a structural constraint for the agent's output.
- Capability inventory: The skill is limited to text generation; it does not request tool access for shell execution, network operations, or file system modifications.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the external files it reads.
- [SAFE]: The skill refers to planning methodologies and benchmarks sourced from Anthropic's public knowledge-work repositories. These references are documented as informational baselines and originate from a trusted organization.
Audit Metadata