ai-daily-digest
Fail
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes content from 92 external RSS feeds to generate summaries and scores. Maliciously crafted feed content could attempt to influence the agent's behavior during analysis.\n
- Ingestion points: RSS feed URLs listed in
scripts/digest.ts.\n - Boundary markers: The skill does not explicitly use delimiters or instructions to ignore embedded commands within the processed feed descriptions.\n
- Capability inventory: The skill can execute shell commands via
bun, write files to the local directory, and convert files using Chrome ormd-to-pdf.\n - Sanitization: The
stripHtmlfunction inscripts/digest.tscleans HTML tags and entities from feed content.\n- [EXTERNAL_DOWNLOADS]: The skill aggregates news from many external domains.\n - Evidence: The file
scripts/digest.tsincludeshttps://timsh.org/rss/, which was flagged as a blacklisted URL by automated scanners. While this is an article source rather than a software dependency, its inclusion requires the agent to fetch data from a site with a poor reputation.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata