The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites to extract positioning and messaging, which creates a potential surface for instructions embedded in those pages to influence the agent.
Ingestion points: Content is retrieved from arbitrary competitor URLs via scripts/analyze_page.py and scripts/competitor_scanner.py as described in Step 1 and Step 2.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when analyzing the scraped content.
Capability inventory: The skill has the capability to execute local Python scripts and perform web searches to identify and scan targets.
Sanitization: There is no mention of sanitizing HTML or marketing copy before it is processed by the model.
[COMMAND_EXECUTION]: The skill invokes local scripts to automate the data collection process.
Evidence: Step 2 explicitly instructs the agent to run python3 scripts/competitor_scanner.py <url>.
[EXTERNAL_DOWNLOADS]: The skill fetches historical snapshots from a well-known archival service.
Evidence: Step 3 fetches historical hero section data from web.archive.org. This is a reputable source for historical web data.

market-competitors