The Agent Skills Directory

[SAFE]: The skill implements a professional marketing automation workflow with clearly defined roles and quality control mechanisms. No malicious intent, credential harvesting, or unauthorized network activity was found.- [PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it ingests untrusted data from marketing briefs and user-provided topics. However, this is inherent to its primary function as a content generator.
Ingestion points: Ingests data from .agents/skill-artifacts/mkt/short-form-brief/[slug]/brief.md, .agents/skill-artifacts/mkt/campaign-plan.md, and the topic argument in SKILL.md.
Boundary markers: The instructions do not specify the use of clear boundary markers or delimiters when passing untrusted brief content to sub-agents.
Capability inventory: The skill is configured with Bash, Write, Read, Grep, and Glob tools, although no malicious use of these tools was detected.
Sanitization: There are no explicit instructions to sanitize or validate the content of the ingested briefs or topics before they are processed by the agents.

social-copy