synthesize-skills
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
scripts/skill-dlto download external repositories from GitHub usinggit clone --depth 1. This is a core part of its research functionality. - [REMOTE_CODE_EXECUTION]: The
scripts/skill-dlscript executesnpx -y skills@latest find, which downloads and runs the latest version of theskillspackage from the npm registry during the search phase. - [COMMAND_EXECUTION]: The skill utilizes several standard shell utilities including
git,curl,find,grep, andsedto perform its discovery and file management tasks. These operations are restricted to the local research corpus and are transparently documented in the scripts. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill supports the use of a
SERPER_API_KEYfor searching via Google's Serper API. This secret is provided by the user and is used strictly for search queries directed togoogle.serper.devas part of the intended search functionality. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest untrusted data from external skill repositories. While this creates a surface for indirect prompt injection, the skill includes detailed references (e.g.,
references/research/source-verification.md) that guide the agent in triaging and verifying sources for quality and security anti-patterns.
Audit Metadata