get-api-docs
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using the
chubCLI tool, includingchub searchto find documentation,chub getto retrieve it, andchub annotateto save local notes. - [EXTERNAL_DOWNLOADS]: The
chub getcommand downloads documentation from external, community-maintained sources. The integrity and safety of this content are dependent on the third-party 'chub' service and its contributors. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it fetches external data that the agent is then instructed to follow closely when writing code.
- Ingestion points: External documentation content is ingested into the agent's context through the output of the
chub getcommand (as described in SKILL.md). - Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore any embedded commands or directives found within the fetched documentation.
- Capability inventory: The environment allows the execution of shell commands (
chub) and local file system modifications (~/.chub/annotations/). - Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved documentation before the agent processes it for code generation.
Audit Metadata