skills/agenta-ai/agenta/sync-findings/Gen Agent Trust Hub

sync-findings

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub PR comments and local review artifacts, creating a surface for indirect prompt injection attacks.\n
  • Ingestion points: The agent reads untrusted data from local findings records and external GitHub PR content (comments, thread state) as described in the SKILL.md workflow steps 2 and 4.\n
  • Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from obeying commands embedded within the synced data.\n
  • Capability inventory: The skill allows the agent to update local documentation (path/findings.md) and interact with remote GitHub PR threads (replying to and resolving comments) as described in SKILL.md workflow steps 3 and 6.\n
  • Sanitization: There is no evidence of content sanitization or validation before the data is written to the findings record or used to determine GitHub thread actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:32 PM
Security Audit — agent-trust-hub — sync-findings