twitter-downloader
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches tweet metadata and media files from external domains, specifically api.fxtwitter.com and api.vxtwitter.com. These are well-known third-party proxy services for accessing Twitter/X content.
- [COMMAND_EXECUTION]: The helper shell script uses standard command-line tools such as curl, jq, sed, and python3. It also includes a function to install missing packages via the apk package manager, which is common in Alpine-based agent environments.
- [PROMPT_INJECTION]: The skill processes untrusted tweet text and media descriptions that are interpolated into the agent's response. This presents a potential surface for indirect prompt injection.
- Ingestion points: scripts/twitter_downloader.sh (fetches external JSON content from fxtwitter/vxtwitter APIs)
- Boundary markers: Absent; tweet text is included in a structured list but lacks explicit delimiters or instructions to ignore embedded commands
- Capability inventory: scripts/twitter_downloader.sh can execute shell commands and write to the local workspace
- Sanitization: None; external metadata is used as-is in the summary generation.
Audit Metadata