The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command (test -n "$APIFY_TOKEN" && echo "set" || echo "missing") to verify the environment state. While used for a benign check, this demonstrates capability for shell execution based on skill instructions.
[CREDENTIALS_UNSAFE]: The skill monitors for the presence of a sensitive environment variable (APIFY_TOKEN). It provides instructions for the user to set this token in their environment, which is a common practice but involves the management of credentials within the agent's context.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted input.
Ingestion points: The skill ingests founder-provided company descriptions, deck summaries, and notes from the user interaction (SKILL.md).
Boundary markers: No delimiters or instructions are used to separate user-provided content from the processing logic.
Capability inventory: The skill has the ability to execute shell commands (environment check) and write files to the local file system (data/normalized/company_profile.json).
Sanitization: There is no mention of sanitizing or escaping the user-provided descriptions before they are written to the structured JSON output, which could lead to data corruption or secondary injection in downstream tools that read the generated file.

clarify-thesis