progressive-summarization
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (articles, transcripts, and notes), which creates an attack surface for indirect prompt injection.
- Ingestion points: External material such as articles or transcripts provided by the user for summarization as described in the "What to ask for" section of SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore any instructions embedded within the source material.
- Capability inventory: The skill specifically instructs the agent to use note-taking tools (like the "Scratchpad connector") to save or update content in external applications based on the summarized output.
- Sanitization: There are no procedures defined for sanitizing or escaping the content from the source text before it is processed, summarized, and sent to external tools.
Audit Metadata