The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to install a third-party tool using the command curl -fsSL https://get.tessl.io | sh. This is a high-risk pattern that executes a remote script with shell privileges without verification or integrity checks.
[COMMAND_EXECUTION]: The file scripts/review.sh is a bash script included in the skill that facilitates the execution of external binaries and the potential installation of remote code via the shell.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to get.tessl.io to retrieve executable content. The source is not a recognized trusted vendor or well-known service infrastructure.
[PROMPT_INJECTION]: The skill is designed to ingest and analyze external SKILL.md files or directories. This represents a surface for indirect prompt injection where malicious instructions embedded in the analyzed data could influence the agent's behavior during the review process.
Ingestion points: SKILL.md and local file paths processed by the tessl skill review command.
Boundary markers: None identified in the prompt instructions to isolate data from commands.
Capability inventory: The agent has the ability to execute shell commands and access the local file system.
Sanitization: No evidence of input validation or sanitization before processing external skill files.

tessl-skill-review