tidyverse-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for processing data frames and strings (e.g., filter, mutate, str_replace_all) that ingest external content without providing specific boundary markers or sanitization instructions for the agent to follow.
- Ingestion points: Variables such as 'data', 'text', and 'large_datasets' in code snippets within SKILL.md.
- Boundary markers: Absent.
- Capability inventory: File writing via 'ggsave' and 'qs2::qs_save' in SKILL.md; parallel process management via 'mirai::daemons' in SKILL.md.
- Sanitization: Absent.
- [DYNAMIC_EXECUTION]: The skill provides instructions for data serialization using the 'qs2' package ('qs_read'), which involves deserializing binary data from local files into R objects.
- [COMMAND_EXECUTION]: The skill utilizes the 'mirai' package for parallel computing, which involves spawning and managing background worker processes (daemons) to handle computations.
Audit Metadata