The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by directing the agent to ingest and summarize content from communications tools. 1. Ingestion points: Reads and processes data from Slack channels, email threads, and company documents referenced in examples/company-newsletter.md, examples/faq-answers.md, and examples/3p-updates.md. 2. Boundary markers: The instructions lack explicit delimiters or warnings to ignore malicious commands that might be embedded in the source data. 3. Capability inventory: The skill primarily performs text processing and formatting; no scripts, shell commands, or network operations are included in the skill files. 4. Sanitization: There are no instructions for the agent to sanitize, validate, or filter content retrieved from the external tools.
[NO_CODE]: The skill consists entirely of Markdown instructions and guidelines; no executable scripts, binaries, or configuration files that trigger code execution are present.

internal-comms