paper-summary
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (URLs, DOIs, or file paths), creating a surface for indirect prompt injection where instructions hidden in the documents could manipulate the agent.
- Ingestion points: User-provided
$ARGUMENTS(URL, DOI, or file path) used to "Fetch/read the paper content" inSKILL.md. - Boundary markers: Absent. The instructions do not provide delimiters or guidance to the agent to treat the fetched content strictly as data rather than instructions.
- Capability inventory: The skill performs network/file reads ("Fetch/read") and file system writes ("Save as ... summary.md") as described in
SKILL.md. - Sanitization: Absent. The content is processed directly for summarization without filtering or validation.
Audit Metadata