The Agent Skills Directory

[PROMPT_INJECTION]: The 'Reverse Engineering' workflow described in 'references/reverse-engineering.md' involves the analysis of large datasets of untrusted social media content. * Ingestion points: The skill instructs the agent to gather and analyze posts and comments from external creators across various social platforms. * Boundary markers: There are no instructions or delimiters provided to distinguish between the agent's instructions and potentially malicious commands embedded in the scraped content. * Capability inventory: The agent is tasked with interpreting and extracting patterns from this external text, which could influence its subsequent behavior. * Sanitization: The skill does not provide any steps for filtering or sanitizing the ingested text.
[NO_CODE]: The skill consists entirely of Markdown documentation and templates. It does not include any executable scripts, binaries, or configuration files that would require runtime execution.

social-content