summarizer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (documents, transcripts, articles) for summarization, which creates a surface where malicious instructions embedded in the source material could potentially influence the agent's behavior. \n
- Ingestion points: The skill in
SKILL.mdis designed to process various source types provided by the user, as identified in Step 1. \n - Boundary markers: The skill lacks explicit instructions or delimiters to isolate source material from instructions or to warn the agent to ignore embedded commands. \n
- Capability inventory: The skill contains no dangerous capabilities such as subprocess calls, file writing, or network operations. \n
- Sanitization: No sanitization or validation of the input source material is performed. \n- [NO_CODE]: The analyzed skill consists entirely of natural language instructions and Markdown templates. No scripts, binaries, or executable code segments were found within the skill files.
Audit Metadata