The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the parallel-cli tool. It interpolates $ARGUMENTS (direct user input) into these commands, which presents a risk of command injection if the underlying agent platform does not properly escape or sanitize the input before passing it to the shell.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes entity data (names, URLs, descriptions) fetched from external internet sources via parallel-cli and presents them back to the user or agent context. Malicious content embedded in these external entities could potentially influence the agent's behavior.
Ingestion points: The output of parallel-cli findall poll is ingested and processed in the 'Response format' section of SKILL.md.
Boundary markers: No explicit boundary markers (e.g., XML tags or delimiters) or 'ignore embedded instructions' warnings are used when processing the external data.
Capability inventory: The skill has access to the Bash tool as defined in the allowed-tools frontmatter.
Sanitization: The skill provides logic to filter for 'noise' (e.g., entries with empty URLs or query-echoing names), but lacks security-focused sanitization to detect or strip instructions from the retrieved data.

parallel-findall