recoup-internal-consulting-linkedin-post-architect
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional Markdown content and reference guides (archetypes, hook formulas, and formatting rules). No shell commands, subprocess calls, or network requests are present.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading from workspace data (such as metrics, case studies, and build logs) and processing content from other drafting agents. While this creates a surface for indirect prompt injection, the skill lacks the capabilities (network access, code execution, or credential access) required to turn such an injection into a security threat.
- [METADATA_POISONING]: The skill's description and metadata accurately reflect its functionality as a structure-layer tool for internal LinkedIn content workflows.
Audit Metadata