skills/delorenj/skills/aws-security/Gen Agent Trust Hub

aws-security

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and summarizes findings from various AWS security services (GuardDuty, Inspector, Macie, Security Hub) which ingest data from external sources. This creates a surface where malicious payloads embedded in findings (e.g., in DNS queries, user-agent strings, or resource identifiers) could attempt to influence agent behavior.\n
  • Ingestion points: Findings containing untrusted data are retrieved using AWS CLI commands as defined in references/guardduty-findings.md, references/inspector-findings.md, references/macie-findings.md, and references/security-hub-findings.md.\n
  • Boundary markers: The instructions do not specify the use of data delimiters or explicit 'ignore' directives to separate the ingested finding content from the agent's instructions.\n
  • Capability inventory: The skill maintains the capability to execute various AWS CLI read operations based on the findings it processes.\n
  • Sanitization: No specific sanitization or filtering logic is provided for the content returned by the AWS security APIs before it is summarized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — aws-security