annotations

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security violations were detected in the instructions or scripts. The skill's operations are consistent with its stated purpose of facilitating IDA Pro database annotations.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests and processes data extracted from external binaries (e.g., disassembly and pseudocode).\n
  • Ingestion points: Untrusted data enters the agent context through SQL tables like pseudocode, comments, and funcs, as seen in SKILL.md and references/annotation-workflows.md.\n
  • Boundary markers: The skill does not define specific delimiters or instructions to treat data from the binary as untrusted or to ignore embedded commands.\n
  • Capability inventory: The agent is configured with the Bash tool (SKILL.md) and has the ability to perform database mutations using UPDATE, INSERT, and DELETE operations across all annotation scripts.\n
  • Sanitization: There is no evidence of sanitization or filtering of the binary-derived content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 03:25 AM
Security Audit — agent-trust-hub — annotations