meeting-no-show-recovery

Fail

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: CRITICALPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from HubSpot records and incorporates it into agent-generated drafts. Malicious content within a meeting subject, contact name, or company field could attempt to manipulate the agent's behavior during the drafting process.
  • Ingestion points: HubSpot meeting engagements, contact records, and company names mentioned in the workflow sections of SKILL.md.
  • Boundary markers: Absent; the skill does not define clear delimiters or provide instructions for the agent to ignore or isolate instructions embedded within the CRM data.
  • Capability inventory: The skill utilizes integrated platform tools to read HubSpot CRM data and generate text output (email drafts).
  • Sanitization: Absent; no specific validation or escaping steps are provided for the external data before it is interpolated into the workflow.
  • [NO_CODE]: The skill consists exclusively of markdown-based instructions and metadata. It does not include Python scripts, Node.js packages, or binary executables.
  • [SAFE]: The metadata field 'author' references 'Builder.org'. While this domain was flagged by automated reputation scans, it is presented as a static metadata string and does not participate in any network operations or execution paths within the skill logic.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 4, 2026, 04:37 PM
Security Audit — agent-trust-hub — meeting-no-show-recovery