github-trending-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/fetch_trending.shto scrape repository data using standard command-line tools. - [EXTERNAL_DOWNLOADS]: The script performs network requests to GitHub's official trending page. As GitHub is a well-known service, this is considered a safe external reference.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by processing external, attacker-influenced content (repository descriptions) without sanitization.
- Ingestion points: Output from the
scripts/fetch_trending.shscript containing third-party text. - Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the fetched data.
- Capability inventory: The agent is instructed to categorize and summarize the resulting text.
- Sanitization: Absent; the script only removes HTML tags and does not filter the text content.
Audit Metadata