The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and evaluation data. It contains no executable scripts, binaries, or configuration files that would perform operations on the host system.
[SAFE]: No sensitive information such as API keys, tokens, or private credentials were found in the skill files.
[SAFE]: No network-based operations or external downloads are performed by this skill. All external references are for informational purposes within the documentation.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface that could be targeted by indirect prompt injection, though the risk is negligible due to the absence of dangerous capabilities.
Ingestion points: The skill instructions in SKILL.md direct the agent to read .agents/product-marketing-context.md and process user-provided prospect information.
Boundary markers: Absent; there are no specific instructions or delimiters to isolate untrusted data or prevent the agent from following instructions embedded within that data.
Capability inventory: Low risk; the agent's actions are restricted to text generation. It lacks the ability to execute system commands, access the network, or modify files.
Sanitization: Absent; no validation or filtering of external input is implemented.
[NO_CODE]: This skill is a 'no-code' skill, meaning it provides instructions and reference data for the AI agent without including any executable scripts or external dependencies.

cold-email