The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several shell commands, including curl, gh, diff, mkdir, and cat, to automate website monitoring, API interaction, and local data management.
[EXTERNAL_DOWNLOADS]: The skill performs automated network requests to external domains such as competitor.com and api.twitter.com to retrieve content for analysis.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes unverified data from external sources.
Ingestion points: Data enters the agent's context through web crawling of competitor pages and social media search results.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the fetched content as untrusted or to disregard potential instructions within that data.
Capability inventory: The skill environment permits shell command execution and local file modifications, which could be exploited if an injection attack successfully manipulates the agent's logic.
Sanitization: The skill does not implement any validation or sanitization of the retrieved HTML or text content before using it to generate reports.
[REMOTE_CODE_EXECUTION]: An automated scan identified a pattern where a remote URL is piped to python3. Manual verification confirms this as a false positive; the skill uses the -c flag to run a hardcoded local extraction script that treats the URL content strictly as data via stdin.

competitive-intel