The Agent Skills Directory

[SAFE]: The skill package is composed entirely of Markdown documentation, templates, and methodology guides. There are no executable scripts, binaries, or automated tasks that could compromise a system. All external URLs provided in the derivation and source files point to well-known or authoritative resources (LinkedIn, Forbes, agency blogs) and are for informational purposes only.
[NO_CODE]: No code files (such as Python scripts, JavaScript, or shell scripts) are present in the skill directory. All logic is contained within natural language instructions for the agent to follow.
[INDIRECT_PROMPT_INJECTION]: The audit workflow involves ingesting and analyzing potentially untrusted external data, specifically customer questions from public forums and responses generated by other AI systems (as described in SKILL.md steps 3 and 5, and references/method.md sections 3 and 4). While this creates an ingestion surface for indirect prompt injection, the skill acts as a manual framework for diagnostic analysis rather than an automated execution pipeline. No boundary markers or specific sanitization steps are defined for the imported data, but the risk is considered low and inherent to the intended primary purpose of the skill.

frankus-geo-audits