goals-and-kpis
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and reference documentation for social media planning. No malicious patterns, such as prompt injection, obfuscation, or unauthorized command execution, were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from
brand-profileandsocial-strategy(ingestion points inSKILL.md). No boundary markers or sanitization logic are explicitly defined in the instructions. However, a capability inventory reveals no network access, shell execution, or file-writing tools across the skill, preventing the exploitation of any instructions found in the ingested data. - [DATA_EXFILTRATION]: No network operations or external communication patterns were found. The skill operates locally within the agent's context to generate planning outputs.
- [REMOTE_CODE_EXECUTION]: There are no scripts, package dependencies, or remote download commands included in this skill. All logic is provided through natural language instructions.
Audit Metadata